1
|
Volinsky-Fremond S, Horeweg N, Andani S, Barkey Wolf J, Lafarge MW, de Kroon CD, Ørtoft G, Høgdall E, Dijkstra J, Jobsen JJ, Lutgens LCHW, Powell ME, Mileshkin LR, Mackay H, Leary A, Katsaros D, Nijman HW, de Boer SM, Nout RA, de Bruyn M, Church D, Smit VTHBM, Creutzberg CL, Koelzer VH, Bosse T. Prediction of recurrence risk in endometrial cancer with multimodal deep learning. Nat Med 2024:10.1038/s41591-024-02993-w. [PMID: 38789645 DOI: 10.1038/s41591-024-02993-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2023] [Accepted: 04/11/2024] [Indexed: 05/26/2024]
Abstract
Predicting distant recurrence of endometrial cancer (EC) is crucial for personalized adjuvant treatment. The current gold standard of combined pathological and molecular profiling is costly, hampering implementation. Here we developed HECTOR (histopathology-based endometrial cancer tailored outcome risk), a multimodal deep learning prognostic model using hematoxylin and eosin-stained, whole-slide images and tumor stage as input, on 2,072 patients from eight EC cohorts including the PORTEC-1/-2/-3 randomized trials. HECTOR demonstrated C-indices in internal (n = 353) and two external (n = 160 and n = 151) test sets of 0.789, 0.828 and 0.815, respectively, outperforming the current gold standard, and identified patients with markedly different outcomes (10-year distant recurrence-free probabilities of 97.0%, 77.7% and 58.1% for HECTOR low-, intermediate- and high-risk groups, respectively, by Kaplan-Meier analysis). HECTOR also predicted adjuvant chemotherapy benefit better than current methods. Morphological and genomic feature extraction identified correlates of HECTOR risk groups, some with therapeutic potential. HECTOR improves on the current gold standard and may help delivery of personalized treatment in EC.
Collapse
Affiliation(s)
| | - Nanda Horeweg
- Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
| | - Sonali Andani
- Department of Computer Science, ETH Zurich, Zurich, Switzerland
- Department of Pathology and Molecular Pathology, University Hospital, University of Zurich, Zurich, Switzerland
- Swiss Institute of Bioinformatics, Lausanne, Switzerland
| | - Jurriaan Barkey Wolf
- Department of Pathology, Leiden University Medical Center, Leiden, The Netherlands
| | - Maxime W Lafarge
- Department of Pathology and Molecular Pathology, University Hospital, University of Zurich, Zurich, Switzerland
| | - Cor D de Kroon
- Department of Gynecology and Obstetrics, Leiden University Medical Center, Leiden, The Netherlands
| | - Gitte Ørtoft
- Department of Gynecology, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | - Estrid Høgdall
- Department of Pathology, Herlev University Hospital, Herlev, Denmark
| | - Jouke Dijkstra
- Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Jan J Jobsen
- Department of Radiation Oncology, Medisch Spectrum Twente, Enschede, The Netherlands
| | | | - Melanie E Powell
- Department of Clinical Oncology, Barts Health NHS Trust, London, UK
| | - Linda R Mileshkin
- Department of Medical Oncology, Peter MacCallum Cancer Center, Melbourne, Victoria, Australia
| | - Helen Mackay
- Department of Medical Oncology and Hematology, Odette Cancer Center Sunnybrook Health Sciences Center, Toronto, Ontario, Canada
| | - Alexandra Leary
- Department Medical Oncology, Gustave Roussy Institute, Villejuif, France
| | - Dionyssios Katsaros
- Department of Surgical Sciences, Gynecologic Oncology, Città della Salute and S Anna Hospital, University of Turin, Turin, Italy
| | - Hans W Nijman
- Department of Obstetrics and Gynecology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Stephanie M de Boer
- Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
| | - Remi A Nout
- Department of Radiotherapy, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Marco de Bruyn
- Department of Obstetrics and Gynecology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - David Church
- Wellcome Centre for Human Genetics, University of Oxford, Oxford, UK
- Oxford NIHR Comprehensive Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| | - Vincent T H B M Smit
- Department of Pathology, Leiden University Medical Center, Leiden, The Netherlands
| | - Carien L Creutzberg
- Department of Radiation Oncology, Leiden University Medical Center, Leiden, The Netherlands
| | - Viktor H Koelzer
- Department of Pathology and Molecular Pathology, University Hospital, University of Zurich, Zurich, Switzerland
- Institute of Medical Genetics and Pathology, University Hospital Basel, Basel, Switzerland
| | - Tjalling Bosse
- Department of Pathology, Leiden University Medical Center, Leiden, The Netherlands.
| |
Collapse
|
2
|
Hahn G, Prokopenko D, Hecker J, Lutz SM, Mullin K, Sejour L, Hide W, Vlachos I, DeSantis S, Tanzi RE, Lange C. Prediction of disease-free survival for precision medicine using cooperative learning on multi-omic data. Brief Bioinform 2024; 25:bbae267. [PMID: 38836403 PMCID: PMC11151121 DOI: 10.1093/bib/bbae267] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2023] [Revised: 04/17/2024] [Accepted: 05/16/2024] [Indexed: 06/06/2024] Open
Abstract
In precision medicine, both predicting the disease susceptibility of an individual and forecasting its disease-free survival are areas of key research. Besides the classical epidemiological predictor variables, data from multiple (omic) platforms are increasingly available. To integrate this wealth of information, we propose new methodology to combine both cooperative learning, a recent approach to leverage the predictive power of several datasets, and polygenic hazard score models. Polygenic hazard score models provide a practitioner with a more differentiated view of the predicted disease-free survival than the one given by merely a point estimate, for instance computed with a polygenic risk score. Our aim is to leverage the advantages of cooperative learning for the computation of polygenic hazard score models via Cox's proportional hazard model, thereby improving the prediction of the disease-free survival. In our experimental study, we apply our methodology to forecast the disease-free survival for Alzheimer's disease (AD) using three layers of data. One layer contains epidemiological variables such as sex, APOE (apolipoprotein E, a genetic risk factor for AD) status and 10 leading principal components. Another layer contains selected genomic loci, and the last layer contains methylation data for selected CpG sites. We demonstrate that the survival curves computed via cooperative learning yield an AUC of around $0.7$, above the state-of-the-art performance of its competitors. Importantly, the proposed methodology returns (1) a linear score that can be easily interpreted (in contrast to machine learning approaches), and (2) a weighting of the predictive power of the involved data layers, allowing for an assessment of the importance of each omic (or other) platform. Similarly to polygenic hazard score models, our methodology also allows one to compute individual survival curves for each patient.
Collapse
Affiliation(s)
- Georg Hahn
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, 02115, Boston, MA, USA
| | - Dmitry Prokopenko
- Department of Neurology, Genetics and Aging Research Unit, McCance Center for Brain Health, Massachusetts General Hospital, 55 Fruit Street, 02114, Boston, MA, USA
| | - Julian Hecker
- Channing Divsion of Network Medicine, Brigham and Women’s Hospital and Harvard Medical School, 75 Francis Street, 02115, Boston, MA, USA
| | - Sharon M Lutz
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, 02115, Boston, MA, USA
| | - Kristina Mullin
- Department of Neurology, Genetics and Aging Research Unit, McCance Center for Brain Health, Massachusetts General Hospital, 55 Fruit Street, 02114, Boston, MA, USA
| | - Leinal Sejour
- Department of Pathology, Beth Israel Deaconess Medical Center, 330 Brookline Avenue, 02215, Boston, MA, USA
| | - Winston Hide
- Department of Pathology, Beth Israel Deaconess Medical Center, 330 Brookline Avenue, 02215, Boston, MA, USA
| | - Ioannis Vlachos
- Department of Pathology, Beth Israel Deaconess Medical Center, 330 Brookline Avenue, 02215, Boston, MA, USA
| | - Stacia DeSantis
- Houston Campus, The University of Texas Health Science Center, 1200 Pressler Street, 77030, Houston, TX, USA
| | - Rudolph E Tanzi
- Department of Neurology, Genetics and Aging Research Unit, McCance Center for Brain Health, Massachusetts General Hospital, 55 Fruit Street, 02114, Boston, MA, USA
| | - Christoph Lange
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, 02115, Boston, MA, USA
| |
Collapse
|
3
|
Peng H, Su M, Guo X, Shi L, Lei T, Yu H, Xu J, Pan X, Chen X. Artificial intelligence-based prognostic model accurately predicts the survival of patients with diffuse large B-cell lymphomas: analysis of a large cohort in China. BMC Cancer 2024; 24:621. [PMID: 38773392 PMCID: PMC11110380 DOI: 10.1186/s12885-024-12337-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2023] [Accepted: 05/03/2024] [Indexed: 05/23/2024] Open
Abstract
BACKGROUND Diffuse large B-cell lymphomas (DLBCLs) display high molecular heterogeneity, but the International Prognostic Index (IPI) considers only clinical indicators and has not been updated to include molecular data. Therefore, we developed a widely applicable novel scoring system with molecular indicators screened by artificial intelligence (AI) that achieves accurate prognostic stratification and promotes individualized treatments. METHODS We retrospectively enrolled a cohort of 401 patients with DLBCL from our hospital, covering the period from January 2015 to January 2019. We included 22 variables in our analysis and assigned them weights using the random survival forest method to establish a new predictive model combining bidirectional long-short term memory (Bi-LSTM) and logistic hazard techniques. We compared the predictive performance of our "molecular-contained prognostic model" (McPM) and the IPI. In addition, we developed a simplified version of the McPM (sMcPM) to enhance its practical applicability in clinical settings. We also demonstrated the improved risk stratification capabilities of the sMcPM. RESULTS Our McPM showed superior predictive accuracy, as indicated by its high C-index and low integrated Brier score (IBS), for both overall survival (OS) and progression-free survival (PFS). The overall performance of the McPM was also better than that of the IPI based on receiver operating characteristic (ROC) curve fitting. We selected five key indicators, including extranodal involvement sites, lactate dehydrogenase (LDH), MYC gene status, absolute monocyte count (AMC), and platelet count (PLT) to establish the sMcPM, which is more suitable for clinical applications. The sMcPM showed similar OS results (P < 0.0001 for both) to the IPI and significantly better PFS stratification results (P < 0.0001 for sMcPM vs. P = 0.44 for IPI). CONCLUSIONS Our new McPM, including both clinical and molecular variables, showed superior overall stratification performance to the IPI, rendering it more suitable for the molecular era. Moreover, our sMcPM may become a widely used and effective stratification tool to guide individual precision treatments and drive new drug development.
Collapse
Affiliation(s)
- Huilin Peng
- Department of Lymphatic Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, 310022, China
| | - Mengmeng Su
- Binjiang Institute of Zhejiang University, Hangzhou, Zhejiang, 310053, China
| | - Xiang Guo
- Zhejiang University of Science & Technology, Hangzhou, Zhejiang, 310027, China
| | - Liang Shi
- Department of Pharmacy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, 310022, China
| | - Tao Lei
- Department of Lymphatic Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, 310022, China
| | - Haifeng Yu
- Department of Lymphatic Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, 310022, China
| | - Jieyu Xu
- Department of Lymphatic Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, 310022, China
| | - Xiaohua Pan
- Binjiang Institute of Zhejiang University, Hangzhou, Zhejiang, 310053, China.
| | - Xi Chen
- Department of Lymphatic Oncology, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, 310022, China.
| |
Collapse
|
4
|
Dong M, Li C, Zhang L, Zhou J, Xiao Y, Zhang T, Jin X, Fang Z, Zhang L, Han Y, Guan J, Weng Z, Cheng N, Wang J. Intertumoral Heterogeneity Based on MRI Radiomic Features Estimates Recurrence in Hepatocellular Carcinoma. J Magn Reson Imaging 2024. [PMID: 38712652 DOI: 10.1002/jmri.29428] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2024] [Revised: 04/16/2024] [Accepted: 04/16/2024] [Indexed: 05/08/2024] Open
Abstract
BACKGROUND Hepatocellular carcinoma (HCC) heterogeneity impacts prognosis, and imaging is a potential indicator. PURPOSE To characterize HCC image subtypes in MRI and correlate subtypes with recurrence. STUDY TYPE Retrospective. POPULATION A total of 440 patients (training cohort = 213, internal test cohort = 140, external test cohort = 87) from three centers. FIELD STRENGTH/SEQUENCE 1.5-T/3.0-T, fast/turbo spin-echo T2-weighted, spin-echo echo-planar diffusion-weighted, contrast-enhanced three-dimensional gradient-recalled-echo T1-weighted with extracellular agents (Gd-DTPA, Gd-DTPA-BMA, and Gd-BOPTA). ASSESSMENT Three-dimensional volume-of-interest of HCC was contoured on portal venous phase, then coregistered with precontrast and late arterial phases. Subtypes were identified using non-negative matrix factorization by analyzing radiomics features from volume-of-interests, and correlated with recurrence. Clinical (demographic and laboratory data), pathological, and radiologic features were compared across subtypes. Among clinical, radiologic features and subtypes, variables with variance inflation factor above 10 were excluded. Variables (P < 0.10) in univariate Cox regression were included in stepwise multivariate analysis. Three recurrence estimation models were built: clinical-radiologic model, subtype model, hybrid model integrating clinical-radiologic characteristics, and subtypes. STATISTICAL TESTS Mann-Whitney U test, Kruskal-Wallis H test, chi-square test, Fisher's exact test, Kaplan-Meier curves, log-rank test, concordance index (C-index). Significance level: P < 0.05. RESULTS Two subtypes were identified across three cohorts (subtype 1:subtype 2 of 86:127, 60:80, and 36:51, respectively). Subtype 1 showed higher microvascular invasion (MVI)-positive rates (53%-57% vs. 26%-31%), and worse recurrence-free survival. Hazard ratio (HR) for the subtype is 6.10 in subtype model. Clinical-radiologic model included alpha-fetoprotein (HR: 3.01), macrovascular invasion (HR: 2.32), nonsmooth tumor margin (HR: 1.81), rim enhancement (HR: 3.13), and intratumoral artery (HR: 2.21). Hybrid model included alpha-fetoprotein (HR: 2.70), nonsmooth tumor margin (HR: 1.51), rim enhancement (HR: 3.25), and subtypes (HR: 5.34). Subtype model was comparable to clinical-radiologic model (C-index: 0.71-0.73 vs. 0.71-0.73), but hybrid model outperformed both (C-index: 0.77-0.79). CONCLUSION MRI radiomics-based clustering identified two HCC subtypes with distinct MVI status and recurrence-free survival. Hybrid model showed superior capability to estimate recurrence. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY STAGE: 2.
Collapse
Affiliation(s)
- Mengshi Dong
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Chao Li
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Lina Zhang
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Jinhui Zhou
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Yuanqiang Xiao
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Tianhui Zhang
- Department of Radiology, Meizhou People's Hospital, Meizhou, China
| | - Xin Jin
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Zebin Fang
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Linqi Zhang
- Department of Radiology, Affiliated Cancer Hospital and Institute of Guangzhou Medical University, Guangzhou, China
| | - Yu Han
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Jiexia Guan
- Department of Pathology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Zijin Weng
- Department of Pathology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Na Cheng
- Department of Pathology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Jin Wang
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| |
Collapse
|
5
|
Oliver M, Allou N, Devineau M, Allyn J, Ferdynus C. A transformer model for cause-specific hazard prediction. BMC Bioinformatics 2024; 25:175. [PMID: 38702609 PMCID: PMC11069215 DOI: 10.1186/s12859-024-05799-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2024] [Accepted: 04/26/2024] [Indexed: 05/06/2024] Open
Abstract
BACKGROUD Modelling discrete-time cause-specific hazards in the presence of competing events and non-proportional hazards is a challenging task in many domains. Survival analysis in longitudinal cohorts often requires such models; notably when the data is gathered at discrete points in time and the predicted events display complex dynamics. Current models often rely on strong assumptions of proportional hazards, that is rarely verified in practice; or do not handle sequential data in a meaningful way. This study proposes a Transformer architecture for the prediction of cause-specific hazards in discrete-time competing risks. Contrary to Multilayer perceptrons that were already used for this task (DeepHit), the Transformer architecture is especially suited for handling complex relationships in sequential data, having displayed state-of-the-art performance in numerous tasks with few underlying assumptions on the task at hand. RESULTS Using synthetic datasets of 2000-50,000 patients, we showed that our Transformer model surpassed the CoxPH, PyDTS, and DeepHit models for the prediction of cause-specific hazard, especially when the proportional assumption did not hold. The error along simulated time outlined the ability of our model to anticipate the evolution of cause-specific hazards at later time steps where few events are observed. It was also superior to current models for prediction of dementia and other psychiatric conditions in the English longitudinal study of ageing cohort using the integrated brier score and the time-dependent concordance index. We also displayed the explainability of our model's prediction using the integrated gradients method. CONCLUSIONS Our model provided state-of-the-art prediction of cause-specific hazards, without adopting prior parametric assumptions on the hazard rates. It outperformed other models in non-proportional hazards settings for both the synthetic dataset and the longitudinal cohort study. We also observed that basic models such as CoxPH were more suited to extremely simple settings than deep learning models. Our model is therefore especially suited for survival analysis on longitudinal cohorts with complex dynamics of the covariate-to-outcome relationship, which are common in clinical practice. The integrated gradients provided the importance scores of input variables, which indicated variables guiding the model in its prediction. This model is ready to be utilized for time-to-event prediction in longitudinal cohorts.
Collapse
Affiliation(s)
- Matthieu Oliver
- Methodological Support Unit, Reunion University Hospital, Saint-Denis, La Réunion, France.
- Clinical Informatics Department, Reunion University Hospital, Saint-Denis, La Réunion, France.
| | - Nicolas Allou
- Clinical Informatics Department, Reunion University Hospital, Saint-Denis, La Réunion, France
- Intensive Care Unit, Reunion University Hospital, Saint-Denis, La Réunion, France
| | - Marjolaine Devineau
- Intensive Care Unit, Reunion University Hospital, Saint-Denis, La Réunion, France
| | - Jèrôme Allyn
- Clinical Informatics Department, Reunion University Hospital, Saint-Denis, La Réunion, France
- Intensive Care Unit, Reunion University Hospital, Saint-Denis, La Réunion, France
- Clinical Research Department, INSERM CIC1410, Saint-Pierre, La Réunion, France
| | - Cyril Ferdynus
- Clinical Informatics Department, Reunion University Hospital, Saint-Denis, La Réunion, France
- Clinical Research Department, INSERM CIC1410, Saint-Pierre, La Réunion, France
| |
Collapse
|
6
|
Cui C, Tang Y, Zhang W. Deep Survival Analysis With Latent Clustering and Contrastive Learning. IEEE J Biomed Health Inform 2024; 28:3090-3101. [PMID: 38319782 DOI: 10.1109/jbhi.2024.3362850] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2024]
Abstract
Survival analysis is employed to analyze the time before the event of interest occurs, which is broadly applied in many fields. The existence of censored data with incomplete supervision information about survival outcomes is one key challenge in survival analysis tasks. Although some progress has been made on this issue recently, the present methods generally treat the instances as separate ones while ignoring their potential correlations, thus rendering unsatisfactory performance. In this study, we propose a novel Deep Survival Analysis model with latent Clustering and Contrastive learning (DSACC). Specifically, we jointly optimize representation learning, latent clustering and survival prediction in a unified framework. In this way, the clusters distribution structure in latent representation space is revealed, and meanwhile the structure of the clusters is well incorporated to improve the ability of survival prediction. Besides, by virtue of the learned clusters, we further propose a contrastive loss function, where the uncensored data in each cluster are set as anchors, and the censored data are treated as positive/negative sample pairs according to whether they belong to the same cluster or not. This design enables the censored data to make full use of the supervision information of the uncensored samples. Through extensive experiments on four popular clinical datasets, we demonstrate that our proposed DSACC achieves advanced performance in terms of both C-index (0.6722, 0.6793, 0.6350, and 0.7943) and Integrated Brier Score (IBS) (0.1616, 0.1826, 0.2028, and 0.1120).
Collapse
|
7
|
Lee HW, Yip TCF, Wong VWS, Lim YS, Chan HLY, Ahn SH, Wong GLH, Choi J. CAMP-B score predicts the risk of hepatocellular carcinoma in patients with chronic hepatitis B after HBsAg seroclearance. Aliment Pharmacol Ther 2024; 59:1223-1235. [PMID: 38425096 DOI: 10.1111/apt.17933] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/10/2023] [Revised: 01/15/2024] [Accepted: 02/20/2024] [Indexed: 03/02/2024]
Abstract
BACKGROUND Risk of hepatocellular carcinoma (HCC) persists after hepatitis B surface antigen (HBsAg) seroclearance in patients with chronic hepatitis B (CHB). AIMS To identify risk factors and construct a predictive model for HCC development. METHODS We retrospectively analysed patients with CHB with HBsAg seroclearance. Primary outcome was HCC development. Factors identified from a multivariate Cox model in the training cohort, consisting of 3476 patients from two Korean hospitals, were used to construct the prediction model. External validation was performed using data from 5255 patients in Hong Kong. RESULTS In the training cohort, HCC occurred in 102 patients during 24,019 person-years of observation (0.43%/year). Risk scores were assigned to cirrhosis (C:3), age ≥50 years (A:2), male sex (M:3) and platelet count <150,000/mm3 (P:1); all were independently associated with an increased risk of HCC in multivariate analysis The time-dependent area under receiver operating characteristic curves for 5, 10 and 15 years in the training and validation cohorts were 0.782, 0.817 and 0.825 and 0.785, 0.771 and 0.796, respectively. In the validation cohort, 85 patients developed HCC (0.24%/year). The corresponding incidence of HCC in the low-, intermediate- and high-risk groups were 0.07%, 0.37% and 0.90%, respectively. CONCLUSIONS The CAMP-B score (cirrhosis, age ≥50 years, male sex and platelet count <150,000/mm3/L) was significantly associated with HCC development after HBsAg seroclearance. CAMP-B score can be easily implemented in real-world clinical practice and helps stratify HCC risk in patients with CHB following HBsAg seroclearance.
Collapse
Affiliation(s)
- Hye Won Lee
- Department of Internal Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Terry Cheuk-Fung Yip
- Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Hong Kong, China
- Medical Data Analytics Centre (MDAC), The Chinese University of Hong Kong, Hong Kong, China
- Institute of Digestive Disease, The Chinese University of Hong Kong, Hong Kong, China
| | - Vincent Wai-Sun Wong
- Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Hong Kong, China
- Medical Data Analytics Centre (MDAC), The Chinese University of Hong Kong, Hong Kong, China
- Institute of Digestive Disease, The Chinese University of Hong Kong, Hong Kong, China
| | - Young-Suk Lim
- Department of Gastroenterology, Liver Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | | | - Sang Hoon Ahn
- Department of Internal Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Grace Lai-Hung Wong
- Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Hong Kong, China
- Medical Data Analytics Centre (MDAC), The Chinese University of Hong Kong, Hong Kong, China
- Institute of Digestive Disease, The Chinese University of Hong Kong, Hong Kong, China
| | - Jonggi Choi
- Department of Gastroenterology, Liver Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| |
Collapse
|
8
|
Keogh RH, Van Geloven N. Prediction Under Interventions: Evaluation of Counterfactual Performance Using Longitudinal Observational Data. Epidemiology 2024; 35:329-339. [PMID: 38630508 DOI: 10.1097/ede.0000000000001713] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/19/2024]
Abstract
Predictions under interventions are estimates of what a person's risk of an outcome would be if they were to follow a particular treatment strategy, given their individual characteristics. Such predictions can give important input to medical decision-making. However, evaluating the predictive performance of interventional predictions is challenging. Standard ways of evaluating predictive performance do not apply when using observational data, because prediction under interventions involves obtaining predictions of the outcome under conditions that are different from those that are observed for a subset of individuals in the validation dataset. This work describes methods for evaluating counterfactual performance of predictions under interventions for time-to-event outcomes. This means we aim to assess how well predictions would match the validation data if all individuals had followed the treatment strategy under which predictions are made. We focus on counterfactual performance evaluation using longitudinal observational data, and under treatment strategies that involve sustaining a particular treatment regime over time. We introduce an estimation approach using artificial censoring and inverse probability weighting that involves creating a validation dataset mimicking the treatment strategy under which predictions are made. We extend measures of calibration, discrimination (c-index and cumulative/dynamic AUCt) and overall prediction error (Brier score) to allow assessment of counterfactual performance. The methods are evaluated using a simulation study, including scenarios in which the methods should detect poor performance. Applying our methods in the context of liver transplantation shows that our procedure allows quantification of the performance of predictions supporting crucial decisions on organ allocation.
Collapse
Affiliation(s)
- Ruth H Keogh
- From the Department of Medical Statistics, London School of Hygiene & Tropical Medicine, London, United Kingdom
| | - Nan Van Geloven
- Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, the Netherlands
| |
Collapse
|
9
|
Shi Y, Horiguchi M, Lu Y. Suggestions on Using Machine Learning Models and Cautions for Analyzing Censored Time-To-Event Outcomes. JCO Precis Oncol 2024; 8:e2400220. [PMID: 38781547 DOI: 10.1200/po.24.00220] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2024] [Accepted: 04/12/2024] [Indexed: 05/25/2024] Open
Affiliation(s)
- Yushu Shi
- Division of Biostatistics, Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY
| | - Miki Horiguchi
- Dana-Farber Cancer Institute, Department of Data Science, Boston, MA
| | - Ying Lu
- Stanford Cancer Institute and Department of Biomedical Data Science, Stanford University School of Medicine, Stanford, CA
| |
Collapse
|
10
|
Rask Kragh Jørgensen R, Bergström F, Eloranta S, Tang Severinsen M, Bjøro Smeland K, Fosså A, Haaber Christensen J, Hutchings M, Bo Dahl-Sørensen R, Kamper P, Glimelius I, E Smedby K, K Parsons S, Mae Rodday A, J Maurer M, M Evens A, C El-Galaly T, Hjort Jakobsen L. Machine Learning-Based Survival Prediction Models for Progression-Free and Overall Survival in Advanced-Stage Hodgkin Lymphoma. JCO Clin Cancer Inform 2024; 8:e2300255. [PMID: 38608215 PMCID: PMC11161240 DOI: 10.1200/cci.23.00255] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2023] [Revised: 02/02/2024] [Accepted: 02/21/2024] [Indexed: 04/14/2024] Open
Abstract
PURPOSE Patients diagnosed with advanced-stage Hodgkin lymphoma (aHL) have historically been risk-stratified using the International Prognostic Score (IPS). This study investigated if a machine learning (ML) approach could outperform existing models when it comes to predicting overall survival (OS) and progression-free survival (PFS). PATIENTS AND METHODS This study used patient data from the Danish National Lymphoma Register for model development (development cohort). The ML model was developed using stacking, which combines several predictive survival models (Cox proportional hazard, flexible parametric model, IPS, principal component, penalized regression) into a single model, and was compared with two versions of IPS (IPS-3 and IPS-7) and the newly developed aHL international prognostic index (A-HIPI). Internal model validation was performed using nested cross-validation, and external validation was performed using patient data from the Swedish Lymphoma Register and Cancer Registry of Norway (validation cohort). RESULTS In total, 707 and 760 patients with aHL were included in the development and validation cohorts, respectively. Examining model performance for OS in the development cohort, the concordance index (C-index) for the ML model, IPS-7, IPS-3, and A-HIPI was found to be 0.789, 0.608, 0.650, and 0.768, respectively. The corresponding estimates in the validation cohort were 0.749, 0.700, 0.663, and 0.741. For PFS, the ML model achieved the highest C-index in both cohorts (0.665 in the development cohort and 0.691 in the validation cohort). The time-varying AUCs for both the ML model and the A-HIPI were consistently higher in both cohorts compared with the IPS models within the first 5 years after diagnosis. CONCLUSION The new prognostic model for aHL on the basis of ML techniques demonstrated a substantial improvement compared with the IPS models, but yielded a limited improvement in predictive performance compared with the A-HIPI.
Collapse
Affiliation(s)
- Rasmus Rask Kragh Jørgensen
- Department of Hematology, Clinical Cancer Research Centre, Aalborg University Hospital, Aalborg, Denmark
- Department of Clinical Medicine, Aalborg University, Aalborg, Denmark
| | - Fanny Bergström
- Clinical Epidemiology Division, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden
| | - Sandra Eloranta
- Clinical Epidemiology Division, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden
| | - Marianne Tang Severinsen
- Department of Hematology, Clinical Cancer Research Centre, Aalborg University Hospital, Aalborg, Denmark
- Department of Clinical Medicine, Aalborg University, Aalborg, Denmark
| | | | - Alexander Fosså
- Department of Oncology, Oslo University Hospital, Oslo, Norway
| | | | - Martin Hutchings
- Department of Hematology, Rigshospitalet, Copenhagen, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | | | - Peter Kamper
- Department of Hematology, Aarhus University Hospital, Aarhus, Denmark
| | - Ingrid Glimelius
- Clinical Epidemiology Division, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden
- Department of Immunology, Genetics and Pathology, Cancer Precision Medicine, Uppsala University, Uppsala, Sweden
| | - Karin E Smedby
- Clinical Epidemiology Division, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden
- Department of Hematology, Karolinska University Hospital, Stockholm, Sweden
| | - Susan K Parsons
- Department of Medicine, Institute for Clinical Research and Health Policy Studies, Tufts Medical Center, Boston, MA
| | - Angie Mae Rodday
- Department of Medicine, Institute for Clinical Research and Health Policy Studies, Tufts Medical Center, Boston, MA
| | - Matthew J Maurer
- Department of Qualitative Health Sciences, Mayo Clinic, Rochester, MN
| | - Andrew M Evens
- Division of Blood Disorders, Rutgers Cancer Institute New Jersey, New Brunswick, NJ
| | - Tarec C El-Galaly
- Department of Hematology, Clinical Cancer Research Centre, Aalborg University Hospital, Aalborg, Denmark
- Department of Clinical Medicine, Aalborg University, Aalborg, Denmark
| | - Lasse Hjort Jakobsen
- Department of Hematology, Clinical Cancer Research Centre, Aalborg University Hospital, Aalborg, Denmark
- Department of Mathematical Sciences, Aalborg University, Aalborg, Denmark
| |
Collapse
|
11
|
Ling Y, Liu Z, Xue JH. Survival Analysis of High-Dimensional Data With Graph Convolutional Networks and Geometric Graphs. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:4876-4886. [PMID: 35862325 DOI: 10.1109/tnnls.2022.3190321] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
This article proposes a survival model based on graph convolutional networks (GCNs) with geometric graphs directly constructed from high-dimensional features. First, we clarify that the graphs used in GCNs play an important role in processing the relational information of samples, and the graphs that align well with the underlying data structure could be beneficial for survival analysis. Second, we show that sparse geometric graphs derived from high-dimensional data are more favorable compared with dense graphs when used in GCNs for survival analysis. Third, from this insight, we propose a model for survival analysis based on GCNs. By using multiple sparse geometric graphs and a proposed sequential forward floating selection algorithm, the new model is able to simultaneously perform survival analysis and unveil the local neighborhoods of samples. The experimental results on real-world datasets show that the proposed survival analysis approach based on GCNs outperforms a variety of existing methods and indicate that geometric graphs can aid survival analysis of high-dimensional data.
Collapse
|
12
|
Xia M, An J, Safford MM, Colantonio LD, Sims M, Reynolds K, Moran AE, Zhang Y. Cardiovascular Risk Associated With Social Determinants of Health at Individual and Area Levels. JAMA Netw Open 2024; 7:e248584. [PMID: 38669015 PMCID: PMC11053380 DOI: 10.1001/jamanetworkopen.2024.8584] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/20/2023] [Accepted: 02/28/2024] [Indexed: 04/29/2024] Open
Abstract
Importance The benefit of adding social determinants of health (SDOH) when estimating atherosclerotic cardiovascular disease (ASCVD) risk is unclear. Objective To examine the association of SDOH at both individual and area levels with ASCVD risks, and to assess if adding individual- and area-level SDOH to the pooled cohort equations (PCEs) or the Predicting Risk of CVD Events (PREVENT) equations improves the accuracy of risk estimates. Design, Setting, and Participants This cohort study included participants data from 4 large US cohort studies. Eligible participants were aged 40 to 79 years without a history of ASCVD. Baseline data were collected from 1995 to 2007; median (IQR) follow-up was 13.0 (9.3-15.0) years. Data were analyzed from September 2023 to February 2024. Exposures Individual- and area-level education, income, and employment status. Main outcomes and measures ASCVD was defined as the composite outcome of nonfatal myocardial infarction, death from coronary heart disease, and fatal or nonfatal stroke. Results A total of 26 316 participants were included (mean [SD] age, 61.0 [9.1] years; 15 494 women [58.9%]; 11 365 Black [43.2%], 703 Chinese American [2.7%], 1278 Hispanic [4.9%], and 12 970 White [49.3%]); 11 764 individuals (44.7%) had at least 1 adverse individual-level SDOH and 10 908 (41.5%) had at least 1 adverse area-level SDOH. A total of 2673 ASCVD events occurred during follow-up. SDOH were associated with increased risk of ASCVD at both the individual and area levels, including for low education (individual: hazard ratio [HR], 1.39 [95% CI, 1.25-1.55]; area: HR, 1.31 [95% CI, 1.20-1.42]), low income (individual: 1.35 [95% CI, 1.25-1.47]; area: HR, 1.28 [95% CI, 1.17-1.40]), and unemployment (individual: HR, 1.61 [95% CI, 1.24-2.10]; area: HR, 1.25 [95% CI, 1.14-1.37]). Adding area-level SDOH alone to the PCEs did not change model discrimination but modestly improved calibration. Furthermore, adding both individual- and area-level SDOH to the PCEs led to a modest improvement in both discrimination and calibration in non-Hispanic Black individuals (change in C index, 0.0051 [95% CI, 0.0011 to 0.0126]; change in scaled integrated Brier score [IBS], 0.396% [95% CI, 0.221% to 0.802%]), and improvement in calibration in White individuals (change in scaled IBS, 0.274% [95% CI, 0.095% to 0.665%]). Adding individual-level SDOH to the PREVENT plus area-level social deprivation index (SDI) equations did not improve discrimination but modestly improved calibration in White participants (change in scaled IBS, 0.182% [95% CI, 0.040% to 0.496%]), Black participants (0.187% [95% CI, 0.039% to 0.501%]), and women (0.289% [95% CI, 0.115% to 0.574%]). Conclusions and Relevance In this cohort study, both individual- and area-level SDOH were associated with ASCVD risk; adding both individual- and area-level SDOH to the PCEs modestly improved discrimination and calibration for estimating ASCVD risk for Black individuals, and adding individual-level SDOH to PREVENT plus SDI also modestly improved calibration. These findings suggest that both individual- and area-level SDOH may be considered in future development of ASCVD risk assessment tools, particularly among Black individuals.
Collapse
Affiliation(s)
- Mengying Xia
- Division of General Medicine, Columbia University Irving Medical Center, New York, New York
| | - Jaejin An
- Department of Research & Evaluation, Kaiser Permanente Southern California, Pasadena
- Department of Health Systems Science, Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, California
| | - Monika M. Safford
- Division of General Internal Medicine, Department of Medicine, Weill Cornell Medicine, New York, New York
| | | | - Mario Sims
- Department of Social Medicine, Population, and Public Health, University of California, Riverside
| | - Kristi Reynolds
- Department of Research & Evaluation, Kaiser Permanente Southern California, Pasadena
- Department of Health Systems Science, Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, California
| | - Andrew E. Moran
- Division of General Medicine, Columbia University Irving Medical Center, New York, New York
| | - Yiyi Zhang
- Division of General Medicine, Columbia University Irving Medical Center, New York, New York
| |
Collapse
|
13
|
Rattsev I, Stearns V, Blackford AL, Hertz DL, Smith KL, Rae JM, Taylor CO. Incorporation of emergent symptoms and genetic covariates improves prediction of aromatase inhibitor therapy discontinuation. JAMIA Open 2024; 7:ooae006. [PMID: 38250582 PMCID: PMC10799747 DOI: 10.1093/jamiaopen/ooae006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2023] [Revised: 08/09/2023] [Accepted: 01/08/2024] [Indexed: 01/23/2024] Open
Abstract
Objectives Early discontinuation is common among breast cancer patients taking aromatase inhibitors (AIs). Although several predictors have been identified, it is unclear how to simultaneously consider multiple risk factors for an individual. We sought to develop a tool for prediction of AI discontinuation and to explore how predictive value of risk factors changes with time. Materials and Methods Survival machine learning was used to predict time-to-discontinuation of AIs in 181 women who enrolled in a prospective cohort. Models were evaluated via time-dependent area under the curve (AUC), c-index, and integrated Brier score. Feature importance was analysis was conducted via Shapley Additive Explanations (SHAP) and time-dependence of their predictive value was analyzed by time-dependent AUC. Personalized survival curves were constructed for risk communication. Results The best-performing model incorporated genetic risk factors and changes in patient-reported outcomes, achieving mean time-dependent AUC of 0.66, and AUC of 0.72 and 0.67 at 6- and 12-month cutoffs, respectively. The most significant features included variants in ESR1 and emergent symptoms. Predictive value of genetic risk factors was highest in the first year of treatment. Decrease in physical function was the strongest independent predictor at follow-up. Discussion and Conclusion Incorporation of genomic and 3-month follow-up data improved the ability of the models to identify the individuals at risk of AI discontinuation. Genetic risk factors were particularly important for predicting early discontinuers. This study provides insight into the complex nature of AI discontinuation and highlights the importance of incorporating genetic risk factors and emergent symptoms into prediction models.
Collapse
Affiliation(s)
- Ilia Rattsev
- Institute for Computational Medicine, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, 21218, United States
- Department of Biomedical Engineering, Johns Hopkins University School of Medicine, Baltimore, MD, 21218, United States
| | - Vered Stearns
- Department of Oncology, Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University School of Medicine, Baltimore, MD, 21287, United States
| | - Amanda L Blackford
- Department of Oncology, Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University School of Medicine, Baltimore, MD, 21287, United States
| | - Daniel L Hertz
- Department of Clinical Pharmacy, University of Michigan College of Pharmacy, Ann Arbor, MI, 48109, United States
| | - Karen L Smith
- Department of Oncology, Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University School of Medicine, Baltimore, MD, 21287, United States
| | - James M Rae
- Department of Internal Medicine, University of Michigan Medical School, Ann Arbor, MI, 48109, United States
- Department of Pharmacology, University of Michigan Medical School, Ann Arbor, MI, 48109, United States
| | - Casey Overby Taylor
- Institute for Computational Medicine, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, 21218, United States
- Department of Biomedical Engineering, Johns Hopkins University School of Medicine, Baltimore, MD, 21218, United States
- Department of General Internal Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, 21205, United States
| |
Collapse
|
14
|
Venturini M, Van Keilegom I, De Corte W, Vens C. Predicting time-to-intubation after critical care admission using machine learning and cured fraction information. Artif Intell Med 2024; 150:102817. [PMID: 38553157 DOI: 10.1016/j.artmed.2024.102817] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 02/19/2024] [Accepted: 02/20/2024] [Indexed: 04/02/2024]
Abstract
Intubation for mechanical ventilation (MV) is one of the most common high-risk procedures performed in Intensive Care Units (ICUs). Early prediction of intubation may have a positive impact by providing timely alerts to clinicians and consequently avoiding high-risk late intubations. In this work, we propose a new machine learning method to predict the time to intubation during the first five days of ICU admission, based on the concept of cure survival models. Our approach combines classification and survival analysis, to effectively accommodate the fraction of patients not at risk of intubation, and provide a better estimate of time to intubation, for patients at risk. We tested our approach and compared it to other predictive models on a dataset collected from a secondary care hospital (AZ Groeninge, Kortrijk, Belgium) from 2015 to 2021, consisting of 3425 ICU stays. Furthermore, we utilised SHAP for feature importance analysis, extracting key insights into the relative significance of variables such as vital signs, blood gases, and patient characteristics in predicting intubation in ICU settings. The results corroborate that our approach improves the prediction of time to intubation in critically ill patients, by using routinely collected data within the first hours of admission in the ICU. Early warning of the need for intubation may be used to help clinicians predict the risk of intubation and rank patients according to their expected time to intubation.
Collapse
Affiliation(s)
- Michela Venturini
- KU Leuven, Campus KULAK-Department of Public Health and Primary Care, Etienne Sabbelaan 53, Kortrijk, 8500, Belgium; ITEC-imec and KU Leuven, Etienne Sabbelaan 51, Kortrijk, 8500, Belgium.
| | - Ingrid Van Keilegom
- Research Centre for Operations Research and Statistics, KU Leuven, Naamsestraat 69, Leuven, 3000, Belgium
| | - Wouter De Corte
- Department of Anesthesiology and Intensive Care Medicine, AZ Groeninge Hospital, President Kennedylaan 4, Kortrijk, 8500, Belgium
| | - Celine Vens
- KU Leuven, Campus KULAK-Department of Public Health and Primary Care, Etienne Sabbelaan 53, Kortrijk, 8500, Belgium; ITEC-imec and KU Leuven, Etienne Sabbelaan 51, Kortrijk, 8500, Belgium.
| |
Collapse
|
15
|
Butner JD, Dogra P, Chung C, Koay EJ, Welsh JW, Hong DS, Cristini V, Wang Z. Hybridizing mechanistic mathematical modeling with deep learning methods to predict individual cancer patient survival after immune checkpoint inhibitor therapy. RESEARCH SQUARE 2024:rs.3.rs-4151883. [PMID: 38586046 PMCID: PMC10996814 DOI: 10.21203/rs.3.rs-4151883/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/09/2024]
Abstract
We present a study where predictive mechanistic modeling is used in combination with deep learning methods to predict individual patient survival probabilities under immune checkpoint inhibitor (ICI) therapy. This hybrid approach enables prediction based on both measures that are calculable from mechanistic models (but may not be directly measurable in the clinic) and easily measurable quantities or characteristics (that are not always readily incorporated into predictive mechanistic models). The mechanistic model we have applied here can predict tumor response from CT or MRI imaging based on key mechanisms underlying checkpoint inhibitor therapy, and in the present work, its parameters were combined with readily-available clinical measures from 93 patients into a hybrid training set for a deep learning time-to-event predictive model. Analysis revealed that training an artificial neural network with both mechanistic modeling-derived and clinical measures achieved higher per-patient predictive accuracy based on event-time concordance, Brier score, and negative binomial log-likelihood-based criteria than when only mechanistic model-derived values or only clinical data were used. Feature importance analysis revealed that both clinical and model-derived parameters play prominent roles in neural network decision making, and in increasing prediction accuracy, further supporting the advantage of our hybrid approach. We anticipate that many existing mechanistic models may be hybridized with deep learning methods in a similar manner to improve predictive accuracy through addition of additional data that may not be readily implemented in mechanistic descriptions.
Collapse
Affiliation(s)
- Joseph D Butner
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Institute for Data Science in Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Master in Clinical Translation Management Program, The Cameron School of Business, University of St. Thomas, Houston, TX 77006, USA
| | - Prashant Dogra
- Mathematics in Medicine Program, Houston Methodist Research Institute, Houston, TX 77030, USA
- Department of Physiology and Biophysics, Weill Cornell Medicine, New York, NY 10065, USA
| | - Caroline Chung
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
- Institute for Data Science in Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - Eugene J Koay
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - James W Welsh
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
| | - David S Hong
- Department of Investigational Cancer Therapeutics, University of Texas MD Anderson Cancer Center, Houston, Texas 77230, USA
| | - Vittorio Cristini
- Mathematics in Medicine Program, Houston Methodist Research Institute, Houston, TX 77030, USA
- Neal Cancer Center, Houston Methodist Research Institute, Houston, TX 77030, USA
- Physiology, Biophysics, and Systems Biology Program, Graduate School of Medical Sciences, Weill Cornell Medicine, New York, NY 10065, USA
- Department of Imaging Physics, University of Texas MD Anderson Cancer Center, Houston, TX 77230, USA
| | - Zhihui Wang
- Mathematics in Medicine Program, Houston Methodist Research Institute, Houston, TX 77030, USA
- Department of Physiology and Biophysics, Weill Cornell Medicine, New York, NY 10065, USA
- Neal Cancer Center, Houston Methodist Research Institute, Houston, TX 77030, USA
- Department of Medical Education, Texas A&M University School of Medicine, Bryan, TX 77807, USA
| |
Collapse
|
16
|
Carrillo-Perez F, Pizurica M, Zheng Y, Nandi TN, Madduri R, Shen J, Gevaert O. Generation of synthetic whole-slide image tiles of tumours from RNA-sequencing data via cascaded diffusion models. Nat Biomed Eng 2024:10.1038/s41551-024-01193-8. [PMID: 38514775 DOI: 10.1038/s41551-024-01193-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2022] [Accepted: 02/29/2024] [Indexed: 03/23/2024]
Abstract
Training machine-learning models with synthetically generated data can alleviate the problem of data scarcity when acquiring diverse and sufficiently large datasets is costly and challenging. Here we show that cascaded diffusion models can be used to synthesize realistic whole-slide image tiles from latent representations of RNA-sequencing data from human tumours. Alterations in gene expression affected the composition of cell types in the generated synthetic image tiles, which accurately preserved the distribution of cell types and maintained the cell fraction observed in bulk RNA-sequencing data, as we show for lung adenocarcinoma, kidney renal papillary cell carcinoma, cervical squamous cell carcinoma, colon adenocarcinoma and glioblastoma. Machine-learning models pretrained with the generated synthetic data performed better than models trained from scratch. Synthetic data may accelerate the development of machine-learning models in scarce-data settings and allow for the imputation of missing data modalities.
Collapse
Affiliation(s)
- Francisco Carrillo-Perez
- Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, School of Medicine, Stanford, CA, USA
| | - Marija Pizurica
- Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, School of Medicine, Stanford, CA, USA
- Internet technology and Data science Lab (IDLab), Ghent University, Ghent, Belgium
| | - Yuanning Zheng
- Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, School of Medicine, Stanford, CA, USA
| | - Tarak Nath Nandi
- Data Science and Learning Division, Argonne National Laboratory, Lemont, IL, USA
| | - Ravi Madduri
- Data Science and Learning Division, Argonne National Laboratory, Lemont, IL, USA
| | - Jeanne Shen
- Department of Pathology, Stanford University, School of Medicine, Palo Alto, CA, USA
| | - Olivier Gevaert
- Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, School of Medicine, Stanford, CA, USA.
- Department of Biomedical Data Science, Stanford University, School of Medicine, Stanford, CA, USA.
| |
Collapse
|
17
|
Wang Y, Kong X, Bi X, Cui L, Yu H, Wu H. ResDeepSurv: A Survival Model for Deep Neural Networks Based on Residual Blocks and Self-attention Mechanism. Interdiscip Sci 2024:10.1007/s12539-024-00617-y. [PMID: 38489147 DOI: 10.1007/s12539-024-00617-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 01/30/2024] [Accepted: 02/01/2024] [Indexed: 03/17/2024]
Abstract
Survival analysis, as a widely used method for analyzing and predicting the timing of event occurrence, plays a crucial role in the medicine field. Medical professionals utilize survival models to gain insight into the effects of patient covariates on the disease, and the correlation with the effectiveness of different treatment strategies. This knowledge is essential for the development of treatment plans and the enhancement of treatment approaches. Conventional survival models, such as the Cox proportional hazards model, require a significant amount of feature engineering or prior knowledge to facilitate personalized modeling. To address these limitations, we propose a novel residual-based self-attention deep neural network for survival modeling, called ResDeepSurv, which combines the benefits of neural networks and the Cox proportional hazards regression model. The model proposed in our study simulates the distribution of survival time and the correlation between covariates and outcomes, but does not impose strict assumptions on the basic distribution of survival data. This approach effectively accounts for both linear and nonlinear risk functions in survival data analysis. The performance of our model in analyzing survival data with various risk functions is on par with or even superior to that of other existing survival analysis methods. Furthermore, we validate the superior performance of our model in comparison to currently existing methods by evaluating multiple publicly available clinical datasets. Through this study, we prove the effectiveness of our proposed model in survival analysis, providing a promising alternative to traditional approaches. The application of deep learning techniques and the ability to capture complex relationships between covariates and survival outcomes without relying on extensive feature engineering make our model a valuable tool for personalized medicine and decision-making in clinical practice.
Collapse
Affiliation(s)
- Yuchen Wang
- School of Software, Shandong University, Jinan, 250101, China
| | - Xianchun Kong
- Department of Pediatric Surgery, Heze Municipal Hospital, Heze, 274000, China
| | - Xiao Bi
- School of Mathematics, Shandong University, Jinan, 250100, China
| | - Lizhen Cui
- School of Software, Shandong University, Jinan, 250101, China
| | - Hong Yu
- School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China
| | - Hao Wu
- School of Software, Shandong University, Jinan, 250101, China.
| |
Collapse
|
18
|
Cerono G, Melaiu O, Chicco D. Clinical Feature Ranking Based on Ensemble Machine Learning Reveals Top Survival Factors for Glioblastoma Multiforme. JOURNAL OF HEALTHCARE INFORMATICS RESEARCH 2024; 8:1-18. [PMID: 38273986 PMCID: PMC10805687 DOI: 10.1007/s41666-023-00138-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2022] [Revised: 07/06/2023] [Accepted: 07/07/2023] [Indexed: 01/27/2024]
Abstract
Glioblastoma multiforme (GM) is a malignant tumor of the central nervous system considered to be highly aggressive and often carrying a terrible survival prognosis. An accurate prognosis is therefore pivotal for deciding a good treatment plan for patients. In this context, computational intelligence applied to data of electronic health records (EHRs) of patients diagnosed with this disease can be useful to predict the patients' survival time. In this study, we evaluated different machine learning models to predict survival time in patients suffering from glioblastoma and further investigated which features were the most predictive for survival time. We applied our computational methods to three different independent open datasets of EHRs of patients with glioblastoma: the Shieh dataset of 84 patients, the Berendsen dataset of 647 patients, and the Lammer dataset of 60 patients. Our survival time prediction techniques obtained concordance index (C-index) = 0.583 in the Shieh dataset, C-index = 0.776 in the Berendsen dataset, and C-index = 0.64 in the Lammer dataset, as best results in each dataset. Since the original studies regarding the three datasets analyzed here did not provide insights about the most predictive clinical features for survival time, we investigated the feature importance among these datasets. To this end, we then utilized Random Survival Forests, which is a decision tree-based algorithm able to model non-linear interaction between different features and might be able to better capture the highly complex clinical and genetic status of these patients. Our discoveries can impact clinical practice, aiding clinicians and patients alike to decide which therapy plan is best suited for their unique clinical status.
Collapse
Affiliation(s)
- Gabriel Cerono
- Department of Neurology, University of California San Francisco, San Francisco, CA USA
| | | | - Davide Chicco
- Dipartimento di Informatica Sistemistica e Comunicazione, Università di Milano-Bicocca, Milan, Italy
- Institute of Health Policy Management and Evaluation, University of Toronto, Toronto, Ontario Canada
| |
Collapse
|
19
|
Mani K, Deng D, Lin C, Wang M, Hsu ML, Zaorsky NG. Causes of death among people living with metastatic cancer. Nat Commun 2024; 15:1519. [PMID: 38374318 PMCID: PMC10876661 DOI: 10.1038/s41467-024-45307-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Accepted: 01/17/2024] [Indexed: 02/21/2024] Open
Abstract
Studying survivorship and causes of death in patients with advanced or metastatic cancer remains an important task. We characterize the causes of death among patients with metastatic cancer, across 13 cancer types and 25 non-cancer causes and predict the risk of death after diagnosis from the diagnosed cancer versus other causes (e.g., stroke, heart disease, etc.). Among 1,030,937 US (1992-2019) metastatic cancer survivors, 82.6% of patients (n = 688,529) died due to the diagnosed cancer, while 17.4% (n = 145,006) died of competing causes. Patients with lung, pancreas, esophagus, and stomach tumors are the most likely to die of their metastatic cancer, while those with prostate and breast cancer have the lowest likelihood. The median survival time among patients living with metastases is 10 months; our Fine and Gray competing risk model predicts 1 year survival with area under the receiver operating characteristic curve of 0.754 (95% CI [0.754, 0.754]). Leading non-cancer deaths are heart disease (32.4%), chronic obstructive and pulmonary disease (7.9%), cerebrovascular disease (6.1%), and infection (4.1%).
Collapse
Affiliation(s)
- Kyle Mani
- Albert Einstein School of Medicine, Bronx, NY, USA
- Department of Radiation Oncology, University Hospitals Seidman Cancer Center and Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - Daxuan Deng
- Department of Public Health Sciences, Penn State College of Medicine, Hershey, PA, USA
| | - Christine Lin
- Department of Radiation Oncology, Penn State Cancer Institute, Hershey, PA, USA
- Department of Radiation Oncology, University Hospitals Seidman Cancer Center and Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - Ming Wang
- Department of Population and Quantitative Health Sciences, School of Medicine, Case Western Reserve University, Cleveland, OH, 44106, USA
| | - Melinda L Hsu
- Division of Hematology and Oncology, University Hospitals Seidman Cancer Center and Case Western Reserve University School of Medicine, Cleveland, OH, USA
| | - Nicholas G Zaorsky
- Department of Radiation Oncology, University Hospitals Seidman Cancer Center and Case Western Reserve University School of Medicine, Cleveland, OH, USA.
| |
Collapse
|
20
|
El Badisy I, BenBrahim Z, Khalis M, Elansari S, ElHitmi Y, Abbass F, Mellas N, El Rhazi K. Risk factors affecting patients survival with colorectal cancer in Morocco: survival analysis using an interpretable machine learning approach. Sci Rep 2024; 14:3556. [PMID: 38346963 PMCID: PMC10861582 DOI: 10.1038/s41598-024-51304-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2023] [Accepted: 01/03/2024] [Indexed: 02/15/2024] Open
Abstract
The aim of our study was to assess the overall survival rates for colorectal cancer at 3 years and to identify associated strong prognostic factors among patients in Morocco through an interpretable machine learning approach. This approach is based on a fully non-parametric survival random forest (RSF), incorporating variable importance and partial dependence effects. The data was povided from a retrospective study of 343 patients diagnosed and followed at Hassan II University Hospital. Covariate selection was performed using the variable importance based on permutation and partial dependence plots were displayed to explore in depth the relationship between the estimated partial effect of a given predictor and survival rates. The predictive performance was measured by two metrics, the Concordance Index (C-index) and the Brier Score (BS). Overall survival rates at 1, 2 and 3 years were, respectively, 87% (SE = 0.02; CI-95% 0.84-0.91), 77% (SE = 0.02; CI-95% 0.73-0.82) and 60% (SE = 0.03; CI-95% 0.54-0.66). In the Cox model after adjustment for all covariates, sex, tumor differentiation had no significant effect on prognosis, but rather tumor site had a significant effect. The variable importance obtained from RSF strengthens that surgery, stage, insurance, residency, and age were the most important prognostic factors. The discriminative capacity of the Cox PH and RSF was, respectively, 0.771 and 0.798 for the C-index while the accuracy of the Cox PH and RSF was, respectively, 0.257 and 0.207 for the BS. This shows that RSF had both better discriminative capacity and predictive accuracy. Our results show that patients who are older than 70, living in rural areas, without health insurance, at a distant stage and who have not had surgery constitute a subgroup of patients with poor prognosis.
Collapse
Affiliation(s)
- Imad El Badisy
- Mohammed VI Center for Research and Innovation, Rabat, Morocco.
- International School of Public Health, Mohammed VI University of Sciences and Health, Casablanca, Morocco.
- INSERM, IRD, SESSTIM, Sciences Economiques & Sociales de la Santé & Traitement de l'Information Médicale, Aix Marseille Univ, Marseille, France.
| | - Zineb BenBrahim
- Faculty of Medicine, Pharmacy & Dental Medicine, Sidi Mohamed Ben Abdillah University, Fez, Morocco
| | - Mohamed Khalis
- Mohammed VI Center for Research and Innovation, Rabat, Morocco
- International School of Public Health, Mohammed VI University of Sciences and Health, Casablanca, Morocco
- Higher Institute of Nursing Professions and Technical Health, Rabat, Morocco
- Laboratory of Biostatistics, Clinical, and Epidemiological Research, Faculty of Medicine and Pharmacy, Department of Public Health, Mohamed V University, Rabat, Morocco
| | - Soukaina Elansari
- Department of Oncology, University Hospital Hassan II, Sidi Mohamed Ben Abdellah University, Fez, Morocco
| | - Youssef ElHitmi
- Department of Oncology, University Hospital Hassan II, Sidi Mohamed Ben Abdellah University, Fez, Morocco
| | - Fouad Abbass
- Laboratory of Epidemiology and Research in Health Sciences, Department of Epidemiology and Public Health, Faculty of Medicine of Fez, Sidi Mohamed Ben Abdillah University, Fez, Morocco
| | - Nawfal Mellas
- Department of Oncology, University Hospital Hassan II, Sidi Mohamed Ben Abdellah University, Fez, Morocco
| | - Karima El Rhazi
- Laboratory of Epidemiology and Research in Health Sciences, Department of Epidemiology and Public Health, Faculty of Medicine of Fez, Sidi Mohamed Ben Abdillah University, Fez, Morocco
| |
Collapse
|
21
|
Payne RD, Guha N, Mallick BK. A Bayesian survival treed hazards model using latent Gaussian processes. Biometrics 2024; 80:ujad009. [PMID: 38364805 DOI: 10.1093/biomtc/ujad009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Revised: 06/27/2023] [Accepted: 11/12/2023] [Indexed: 02/18/2024]
Abstract
Survival models are used to analyze time-to-event data in a variety of disciplines. Proportional hazard models provide interpretable parameter estimates, but proportional hazard assumptions are not always appropriate. Non-parametric models are more flexible but often lack a clear inferential framework. We propose a Bayesian treed hazards partition model that is both flexible and inferential. Inference is obtained through the posterior tree structure and flexibility is preserved by modeling the log-hazard function in each partition using a latent Gaussian process. An efficient reversible jump Markov chain Monte Carlo algorithm is accomplished by marginalizing the parameters in each partition element via a Laplace approximation. Consistency properties for the estimator are established. The method can be used to help determine subgroups as well as prognostic and/or predictive biomarkers in time-to-event data. The method is compared with some existing methods on simulated data and a liver cirrhosis dataset.
Collapse
Affiliation(s)
- Richard D Payne
- Eli Lilly & Company, Lilly Corporate Center, Indianapolis, IN, 46285, United States
| | - Nilabja Guha
- Department of Mathematical Sciences, University of Massachusetts Lowell, One University Avenue, Lowell, Massachusetts, 01852, United States
| | - Bani K Mallick
- Department of Statistics, Texas A&M University, 3143 TAMU, College Station, TX, 77843-3143, United States
| |
Collapse
|
22
|
Lee KH, Choi GH, Yun J, Choi J, Goh MJ, Sinn DH, Jin YJ, Kim MA, Yu SJ, Jang S, Lee SK, Jang JW, Lee JS, Kim DY, Cho YY, Kim HJ, Kim S, Kim JH, Kim N, Kim KM. Machine learning-based clinical decision support system for treatment recommendation and overall survival prediction of hepatocellular carcinoma: a multi-center study. NPJ Digit Med 2024; 7:2. [PMID: 38182886 PMCID: PMC10770025 DOI: 10.1038/s41746-023-00976-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Accepted: 11/29/2023] [Indexed: 01/07/2024] Open
Abstract
The treatment decisions for patients with hepatocellular carcinoma are determined by a wide range of factors, and there is a significant difference between the recommendations of widely used staging systems and the actual initial treatment choices. Herein, we propose a machine learning-based clinical decision support system suitable for use in multi-center settings. We collected data from nine institutions in South Korea for training and validation datasets. The internal and external datasets included 935 and 1750 patients, respectively. We developed a model with 20 clinical variables consisting of two stages: the first stage which recommends initial treatment using an ensemble voting machine, and the second stage, which predicts post-treatment survival using a random survival forest algorithm. We derived the first and second treatment options from the results with the highest and the second-highest probabilities given by the ensemble model and predicted their post-treatment survival. When only the first treatment option was accepted, the mean accuracy of treatment recommendation in the internal and external datasets was 67.27% and 55.34%, respectively. The accuracy increased to 87.27% and 86.06%, respectively, when the second option was included as the correct answer. Harrell's C index, integrated time-dependent AUC curve, and integrated Brier score of survival prediction in the internal and external datasets were 0.8381 and 0.7767, 91.89 and 86.48, 0.12, and 0.14, respectively. The proposed system can assist physicians by providing data-driven predictions for reference from other larger institutions or other physicians within the same institution when making treatment decisions.
Collapse
Affiliation(s)
- Kyung Hwa Lee
- Department of Radiation Oncology, Korea University Guro Hospital, Korea University College of Medicine, Seoul, Republic of Korea
| | - Gwang Hyeon Choi
- Department of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University, Seongnam, Republic of Korea
| | - Jihye Yun
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Jonggi Choi
- Department of Gastroenterology, Asan Liver Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea
| | - Myung Ji Goh
- Department of Internal Medicine, Samsung Medical Center, Seoul, Republic of Korea
| | - Dong Hyun Sinn
- Department of Internal Medicine, Samsung Medical Center, Seoul, Republic of Korea
| | - Young Joo Jin
- Department of Internal Medicine, Inha University Hospital, Incheon, Republic of Korea
| | - Minseok Albert Kim
- Department of Internal Medicine, Seoul National University Hospital, Seoul National University, Seoul, Republic of Korea
| | - Su Jong Yu
- Department of Internal Medicine, Seoul National University Hospital, Seoul National University, Seoul, Republic of Korea
| | - Sangmi Jang
- Department of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University, Seongnam, Republic of Korea
- Department of Internal Medicine, Inha University Hospital, Incheon, Republic of Korea
| | - Soon Kyu Lee
- Department of Internal Medicine, Seoul St. Mary's Hospital, Seoul, Republic of Korea
- Department of Internal Medicine, Incheon St. Mary's Hospital, Incheon, Republic of Korea
| | - Jeong Won Jang
- Department of Internal Medicine, Seoul St. Mary's Hospital, Seoul, Republic of Korea
| | - Jae Seung Lee
- Department of Internal Medicine, Seoul Severance Hospital, Seoul, Republic of Korea
| | - Do Young Kim
- Department of Internal Medicine, Seoul Severance Hospital, Seoul, Republic of Korea
| | - Young Youn Cho
- Department of Internal Medicine, Chung-Ang University Hospital, Seoul, Republic of Korea
| | - Hyung Joon Kim
- Department of Internal Medicine, Chung-Ang University Hospital, Seoul, Republic of Korea
| | - Sehwa Kim
- Department of Internal Medicine, Korea University Guro Hospital, Korea University College of Medicine, Seoul, Republic of Korea
- Department of Internal Medicine, Bundang Jesaeng General Hospital, Seongnam, Republic of Korea
| | - Ji Hoon Kim
- Department of Internal Medicine, Korea University Guro Hospital, Korea University College of Medicine, Seoul, Republic of Korea
| | - Namkug Kim
- Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
- Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
| | - Kang Mo Kim
- Department of Gastroenterology, Asan Liver Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
| |
Collapse
|
23
|
Öztürk Ö, Uzun NN, Feyzioğlu Ö, Şahin D, Sarıtaş F, Tezcan ME. Investigation of factors affecting physical activity level in patients with primary Sjögren's syndrome. ARP RHEUMATOLOGY 2024; 3:40-48. [PMID: 38368548 DOI: 10.63032/bfol5172] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/12/2024]
Abstract
OBJECTIVES This study aimed to determine physical activity levels and understand the factors influencing an active lifestyle among patients with primary Sjögren's syndrome (pSS). METHODS Ninety-seven patients participated in this multicentric study. Physical activity levels were assessed using the International Physical Activity Questionnaire-Short Form (IPAQ-SF). The Inflammatory Arthritis Facilitators and Barriers (IFAB) questionnaire was used to evaluate perceived barriers and facilitators to physical activity. RESULTS Forty-six patients were physically inactive and the rest of them were moderately active. Commonly identified barriers included a lack of motivation, fatigue, and pain. Conversely, knowledge of the health and mood benefits for physical activity emerged as a key motivator. Patients with better scores on facilitators and lower scores on barriers exhibited higher physical activity levels (p < 0.05). Notably, a high level of perceived facilitators of physical activity (odds ratio [OR]: 1.02; 95% confidence interval [CI], 1.00 – 1.05) and reduced pain (OR: 0.81; 95% CI: 0.69 – 0.95) were linked to an active lifestyle. CONCLUSIONS This study emphasizes the role of motivation and awareness of the benefits of physical activity for health and mood in driving physical activity for patients with primary Sjögren’s syndrome. Tailored physical activity programs that address psychological aspects and disease-related pain, and fatigue should be designed to counter sedentary lifestyles in pSS patients.
Collapse
Affiliation(s)
| | | | | | | | - Fatih Sarıtaş
- University of Health Sciences, Haydarpaşa Numune Research and Training Hospital
| | | |
Collapse
|
24
|
Bouaziz O. Assessing model prediction performance for the expected cumulative number of recurrent events. LIFETIME DATA ANALYSIS 2024; 30:262-289. [PMID: 37975951 DOI: 10.1007/s10985-023-09610-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/27/2023] [Accepted: 09/19/2023] [Indexed: 11/19/2023]
Abstract
In a recurrent event setting, we introduce a new score designed to evaluate the prediction ability, for a given model, of the expected cumulative number of recurrent events. This score can be seen as an extension of the Brier Score for single time to event data but works for recurrent events with or without a terminal event. Theoretical results are provided that show that under standard assumptions in a recurrent event context, our score can be asymptotically decomposed as the sum of the theoretical mean squared error between the model and the true expected cumulative number of recurrent events and an inseparability term that does not depend on the model. This decomposition is further illustrated on simulations studies. It is also shown that this score should be used in comparison with a reference model, such as a nonparametric estimator that does not include the covariates. Finally, the score is applied for the prediction of hospitalisations on a dataset of patients suffering from atrial fibrillation and a comparison of the prediction performances of different models, such as the Cox model, the Aalen Model or the Ghosh and Lin model, is investigated.
Collapse
|
25
|
Tanner KT, Keogh RH, Coupland CAC, Hippisley-Cox J, Diaz-Ordaz K. Dynamic updating of clinical survival prediction models in a changing environment. Diagn Progn Res 2023; 7:24. [PMID: 38082429 PMCID: PMC10714456 DOI: 10.1186/s41512-023-00163-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/16/2023] [Accepted: 10/17/2023] [Indexed: 01/31/2024] Open
Abstract
BACKGROUND Over time, the performance of clinical prediction models may deteriorate due to changes in clinical management, data quality, disease risk and/or patient mix. Such prediction models must be updated in order to remain useful. In this study, we investigate dynamic model updating of clinical survival prediction models. In contrast to discrete or one-time updating, dynamic updating refers to a repeated process for updating a prediction model with new data. We aim to extend previous research which focused largely on binary outcome prediction models by concentrating on time-to-event outcomes. We were motivated by the rapidly changing environment seen during the COVID-19 pandemic where mortality rates changed over time and new treatments and vaccines were introduced. METHODS We illustrate three methods for dynamic model updating: Bayesian dynamic updating, recalibration, and full refitting. We use a simulation study to compare performance in a range of scenarios including changing mortality rates, predictors with low prevalence and the introduction of a new treatment. Next, the updating strategies were applied to a model for predicting 70-day COVID-19-related mortality using patient data from QResearch, an electronic health records database from general practices in the UK. RESULTS In simulated scenarios with mortality rates changing over time, all updating methods resulted in better calibration than not updating. Moreover, dynamic updating outperformed ad hoc updating. In the simulation scenario with a new predictor and a small updating dataset, Bayesian updating improved the C-index over not updating and refitting. In the motivating example with a rare outcome, no single updating method offered the best performance. CONCLUSIONS We found that a dynamic updating process outperformed one-time discrete updating in the simulations. Bayesian updating offered good performance overall, even in scenarios with new predictors and few events. Intercept recalibration was effective in scenarios with smaller sample size and changing baseline hazard. Refitting performance depended on sample size and produced abrupt changes in hazard ratio estimates between periods.
Collapse
Affiliation(s)
- Kamaryn T Tanner
- Department of Medical Statistics, London School of Hygiene and Tropical Medicine, London, WC1E 7HT, UK.
| | - Ruth H Keogh
- Department of Medical Statistics, London School of Hygiene and Tropical Medicine, London, WC1E 7HT, UK
| | - Carol A C Coupland
- Nuffield Department of Primary Health Care Sciences, University of Oxford, Oxford, OX2 6HT, UK
- Centre for Academic Primary Care, University of Nottingham, Nottingham, NG7 2UH, UK
| | - Julia Hippisley-Cox
- Nuffield Department of Primary Health Care Sciences, University of Oxford, Oxford, OX2 6HT, UK
| | - Karla Diaz-Ordaz
- Department of Statistical Science, University College London, London, WC1E 6BT, UK
| |
Collapse
|
26
|
Sud M, Sivaswamy A, Austin PC, Anderson TJ, Naimark DMJ, Farkouh ME, Lee DS, Roifman I, Thanassoulis G, Tu K, Udell JA, Wijeysundera HC, Ko DT. Development and Validation of the CANHEART Population-Based Laboratory Prediction Models for Atherosclerotic Cardiovascular Disease. Ann Intern Med 2023; 176:1638-1647. [PMID: 38079638 DOI: 10.7326/m23-1345] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/20/2023] Open
Abstract
BACKGROUND Prediction of atherosclerotic cardiovascular disease (ASCVD) in primary prevention assessments exclusively with laboratory results may facilitate automated risk reporting and improve uptake of preventive therapies. OBJECTIVE To develop and validate sex-specific prediction models for ASCVD using age and routine laboratory tests and compare their performance with that of the pooled cohort equations (PCEs). DESIGN Derivation and validation of the CANHEART (Cardiovascular Health in Ambulatory Care Research Team) Lab Models. SETTING Population-based cohort study in Ontario, Canada. PARTICIPANTS A derivation and internal validation cohort of adults aged 40 to 75 years without cardiovascular disease from April 2009 to December 2015; an external validation cohort of primary care patients from January 2010 to December 2014. MEASUREMENTS Age and laboratory predictors measured in the outpatient setting included serum total cholesterol, high-density lipoprotein cholesterol, triglycerides, hemoglobin, mean corpuscular volume, platelets, leukocytes, estimated glomerular filtration rate, and glucose. The ASCVD outcomes were defined as myocardial infarction, stroke, and death from ischemic heart or cerebrovascular disease within 5 years. RESULTS Sex-specific models were developed and internally validated in 2 160 497 women and 1 833 147 men. They were well calibrated, with relative differences less than 1% between mean predicted and observed risk for both sexes. The c-statistic was 0.77 in women and 0.71 in men. External validation in 31 697 primary care patients showed a relative difference less than 14% and an absolute difference less than 0.3 percentage points in mean predicted and observed risks for both sexes. The c-statistics for the laboratory models were 0.72 for both sexes and were not statistically significantly different from those for the PCEs in women (change in c-statistic, -0.01 [95% CI, -0.03 to 0.01]) or men (change in c-statistic, -0.01 [CI, -0.04 to 0.02]). LIMITATION Medication use was not available at the population level. CONCLUSION The CANHEART Lab Models predict ASCVD with similar accuracy to more complex models, such as the PCEs. PRIMARY FUNDING SOURCE Canadian Institutes of Health Research.
Collapse
Affiliation(s)
- Maneesh Sud
- Schulich Heart Program, Sunnybrook Health Sciences Centre, University of Toronto; Institute of Health Policy, Management and Evaluation, University of Toronto; ICES; and Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada (M.S., I.R., H.C.W., D.T.K.)
| | | | - Peter C Austin
- Institute of Health Policy, Management and Evaluation, University of Toronto, and ICES, Toronto, Ontario, Canada (P.C.A.)
| | - Todd J Anderson
- Libin Cardiovascular Institute and Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada (T.J.A.)
| | - David M J Naimark
- Institute of Health Policy, Management and Evaluation, University of Toronto; ICES; and Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada (D.M.J.N.)
| | - Michael E Farkouh
- Academic Affairs, Cedars-Sinai Health System, Los Angeles, California (M.E.F.)
| | - Douglas S Lee
- Institute of Health Policy, Management and Evaluation, University of Toronto; ICES; Temerty Faculty of Medicine, University of Toronto; Peter Munk Cardiac Centre, University Health Network, University of Toronto; and Ted Rogers Centre for Heart Research, Toronto, Ontario, Canada (D.S.L.)
| | - Idan Roifman
- Schulich Heart Program, Sunnybrook Health Sciences Centre, University of Toronto; Institute of Health Policy, Management and Evaluation, University of Toronto; ICES; and Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada (M.S., I.R., H.C.W., D.T.K.)
| | - George Thanassoulis
- Department of Medicine, McGill University, and Preventive and Genomic Cardiology, McGill University Health Centre, Montreal, Quebec, Canada (G.T.)
| | - Karen Tu
- Toronto Western Family Health Team, University Health Network, North York General Hospital, and Department of Family and Community Medicine, Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada (K.T.)
| | - Jacob A Udell
- Institute of Health Policy, Management and Evaluation, University of Toronto; ICES; Temerty Faculty of Medicine, University of Toronto; Peter Munk Cardiac Centre, University Health Network, University of Toronto; and Women's College Hospital, University of Toronto, Toronto, Ontario, Canada (J.A.U.)
| | - Harindra C Wijeysundera
- Schulich Heart Program, Sunnybrook Health Sciences Centre, University of Toronto; Institute of Health Policy, Management and Evaluation, University of Toronto; ICES; and Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada (M.S., I.R., H.C.W., D.T.K.)
| | - Dennis T Ko
- Schulich Heart Program, Sunnybrook Health Sciences Centre, University of Toronto; Institute of Health Policy, Management and Evaluation, University of Toronto; ICES; and Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada (M.S., I.R., H.C.W., D.T.K.)
| |
Collapse
|
27
|
Ai D, Cui C, Tang Y, Wang Y, Zhang N, Zhang C, Zhen Y, Li G, Huang K, Liu G, Chen Z, Zhang W, Wu R. Machine learning model for predicting physical activity related bleeding risk in Chinese boys with haemophilia A. Thromb Res 2023; 232:43-53. [PMID: 37931538 DOI: 10.1016/j.thromres.2023.10.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Revised: 10/11/2023] [Accepted: 10/20/2023] [Indexed: 11/08/2023]
Abstract
BACKGROUND Physical activity is a crucial part of an active lifestyle for haemophiliac children. However, the fear of bleeds has been identified as barriers to participating physical activity for haemophiliac children even with prophylaxis. Lack of evidence and metrics driven by data is key problem. OBJECTIVES We aim to develop machine learning models based on clinical data with multiple potential factors considered to predict risk of physical activity bleeding for haemophilia children with prophylaxis. METHODS From this cohort study, we collected information on 98 haemophiliac children with adequate prophylaxis (trough FVIII:C level > 1 %). The involved potential predictor variables include demographic information, treatment information, physical activity, joint evaluation, and pharmacokinetic parameters, etc. We applied CoxPH, Random Survival Forests (RSF) and DeepSurv to construct prediction models for the risk of bleeding during physical activities. All three survival analysis models were internally and externally validated. RESULTS A total of 98 patients were enrolled in this study. Their median age was 7.9 (5.5, 10.2) years. The CoxPH, RSF and DeepSurv models' discriminative and calibration abilities were all high, and the RSF model had the best performance (Internal validation: C-index, 0.7648 ± 0.0139; Brier Score, 0.1098 ± 0.0015; External validation: C-index, 0.7260 ± 0.0154; Brier Score, 0.0930 ± 0.0018). The prediction curves demonstrated that the developed RSF model can distinguish the risks well between bleeding and non-bleeding patients, as well as patients with different levels of physical activity. Meanwhile, the feature importance analysis confirmed that physical activity bleeding was deduced by comprehensive effects of various factors, and the importance of different factors on bleeding outcome is discrepant. CONCLUSIONS This study revealed from the mechanism that it is necessary to incorporate multiple factors to accurately predict physical activity related bleeding risk. In clinical practice, the designed machine learning models can provide guidance for children with haemophilia A to positively participate in physical activity.
Collapse
Affiliation(s)
- Di Ai
- Haemophilia Comprehensive Care Center, Hematology Center, Beijing Key Laboratory of Pediatric Hematology-Oncology, National Key Discipline of Pediatrics (Capital Medical University), Key Laboratory of Major Diseases in Children, Ministry of Education, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, 100045, China
| | - Chang Cui
- State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
| | - Yongqiang Tang
- State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
| | - Yan Wang
- Department of Rehabilitation, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, China
| | - Ningning Zhang
- Department of Radiology, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, China
| | - Chenyang Zhang
- State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
| | - Yingzi Zhen
- Haemophilia Comprehensive Care Center, Hematology Center, Beijing Key Laboratory of Pediatric Hematology-Oncology, National Key Discipline of Pediatrics (Capital Medical University), Key Laboratory of Major Diseases in Children, Ministry of Education, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, 100045, China
| | - Gang Li
- Hematologic Disease Laboratory, Beijing Pediatric Research Institute, Beijing Children's Hospital, Capital Medical University, Beijing, China
| | - Kun Huang
- Haemophilia Comprehensive Care Center, Hematology Center, Beijing Key Laboratory of Pediatric Hematology-Oncology, National Key Discipline of Pediatrics (Capital Medical University), Key Laboratory of Major Diseases in Children, Ministry of Education, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, 100045, China
| | - Guoqing Liu
- Haemophilia Comprehensive Care Center, Hematology Center, Beijing Key Laboratory of Pediatric Hematology-Oncology, National Key Discipline of Pediatrics (Capital Medical University), Key Laboratory of Major Diseases in Children, Ministry of Education, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, 100045, China
| | - Zhenping Chen
- Hematologic Disease Laboratory, Beijing Pediatric Research Institute, Beijing Children's Hospital, Capital Medical University, Beijing, China.
| | - Wensheng Zhang
- State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
| | - Runhui Wu
- Haemophilia Comprehensive Care Center, Hematology Center, Beijing Key Laboratory of Pediatric Hematology-Oncology, National Key Discipline of Pediatrics (Capital Medical University), Key Laboratory of Major Diseases in Children, Ministry of Education, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, 100045, China.
| |
Collapse
|
28
|
Kanwal F, Khaderi S, Singal AG, Marrero JA, Asrani SK, Amos CI, Thrift AP, Kramer JR, Yu X, Cao Y, Luster M, Al-Sarraj A, Ning J, El-Serag HB. Risk Stratification Model for Hepatocellular Cancer in Patients With Cirrhosis. Clin Gastroenterol Hepatol 2023; 21:3296-3304.e3. [PMID: 37390101 PMCID: PMC10661677 DOI: 10.1016/j.cgh.2023.04.019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Revised: 04/07/2023] [Accepted: 04/13/2023] [Indexed: 07/02/2023]
Abstract
BACKGROUND & AIMS The available risk stratification indices for hepatocellular cancer (HCC) have limited applicability. We developed and externally validated an HCC risk stratification index in U.S. cohorts of patients with cirrhosis. METHODS We used data from 2 prospective U.S. cohorts to develop the risk index. Patients with cirrhosis were enrolled from 8 centers and followed until development of HCC, death, or December 31, 2021. We identified an optimal set of predictors with the highest discriminatory ability (C-index) for HCC. The predictors were refit using competing risk regression and its predictive performance was evaluated using the area under the receiver-operating characteristic curve (AUROC). External validation was performed in a cohort of 21,550 patients with cirrhosis seen in the U.S Veterans Affairs system between 2018 and 2019 with follow-up through 2021. RESULTS We developed the model in 2431 patients (mean age 60 years, 31% women, 24% cured hepatitis C, 16% alcoholic liver disease, and 29% nonalcoholic fatty liver disease). The selected model had a C-index of 0.77 (95% confidence interval [CI], 0.73-0.81), and the predictors were age, sex, smoking, alcohol use, body mass index, etiology, α-fetoprotein, albumin, alanine aminotransferase, and platelet levels. The AUROCs were 0.75 (95% CI, 0.65-0.85) at 1 year and 0.77 (95% CI, 0.71-0.83) at 2 years, and the model was well calibrated. In the external validation cohort, the AUROC at 2 years was 0.70 with excellent calibration. CONCLUSION The risk index, including objective and routinely available risk factors, can differentiate patients with cirrhosis who will develop HCC and help guide discussions regarding HCC surveillance and prevention. Future studies are needed for additional external validation and refinement of risk stratification.
Collapse
Affiliation(s)
- Fasiha Kanwal
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, Houston, Texas; Section of Health Services Research, Department of Medicine, Baylor College of Medicine, Houston, Texas; VA HSR&D Center for Innovatio ns in Quality, Effectiveness, and Safety, Michael E. DeBakey Veterans Affairs Medical Center, Houston, Texas.
| | - Saira Khaderi
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, Houston, Texas
| | - Amit G Singal
- Division of Digestive and Liver Diseases, Department of Medicine, UT Southwestern Medical Center, Dallas, Texas
| | - Jorge A Marrero
- Division of Digestive and Liver Diseases, Department of Medicine, UT Southwestern Medical Center, Dallas, Texas
| | - Sumeet K Asrani
- Division of Gastroenterology, Department of Medicine, Baylor University Medical Center, Dallas, Texas
| | - Christopher I Amos
- Section of Epidemiology, Department of Medicine, Baylor College of Medicine, Houston, Texas
| | - Aaron P Thrift
- Section of Epidemiology, Department of Medicine, Baylor College of Medicine, Houston, Texas
| | - Jennifer R Kramer
- Section of Health Services Research, Department of Medicine, Baylor College of Medicine, Houston, Texas; VA HSR&D Center for Innovatio ns in Quality, Effectiveness, and Safety, Michael E. DeBakey Veterans Affairs Medical Center, Houston, Texas
| | - Xian Yu
- Section of Health Services Research, Department of Medicine, Baylor College of Medicine, Houston, Texas; VA HSR&D Center for Innovatio ns in Quality, Effectiveness, and Safety, Michael E. DeBakey Veterans Affairs Medical Center, Houston, Texas
| | - Yumei Cao
- Section of Health Services Research, Department of Medicine, Baylor College of Medicine, Houston, Texas; VA HSR&D Center for Innovatio ns in Quality, Effectiveness, and Safety, Michael E. DeBakey Veterans Affairs Medical Center, Houston, Texas
| | - Michelle Luster
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, Houston, Texas
| | - Abeer Al-Sarraj
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, Houston, Texas; Section of Health Services Research, Department of Medicine, Baylor College of Medicine, Houston, Texas; VA HSR&D Center for Innovatio ns in Quality, Effectiveness, and Safety, Michael E. DeBakey Veterans Affairs Medical Center, Houston, Texas
| | - Jing Ning
- Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Hashem B El-Serag
- Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, Houston, Texas; Section of Health Services Research, Department of Medicine, Baylor College of Medicine, Houston, Texas; VA HSR&D Center for Innovatio ns in Quality, Effectiveness, and Safety, Michael E. DeBakey Veterans Affairs Medical Center, Houston, Texas.
| |
Collapse
|
29
|
Kong F, Yang H, Wang Q, Wei Z, Ye X. A prognostic model for predicting progression-free survival in patients with advanced non-small cell lung cancer after image-guided microwave ablation plus chemotherapy. Eur Radiol 2023; 33:7438-7449. [PMID: 37318606 PMCID: PMC10598089 DOI: 10.1007/s00330-023-09804-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2022] [Revised: 03/29/2023] [Accepted: 04/21/2023] [Indexed: 06/16/2023]
Abstract
OBJECTIVES This study aimed to build and validate a prediction model that can predict progression-free survival (PFS) in patients with advanced non-small cell lung cancer (NSCLC) after image-guided microwave ablation (MWA) plus chemotherapy. METHODS Data from a previous multi-center randomized controlled trial (RCT) was used and assigned to either the training data set or the external validation data set according to the location of the centers. Potential prognostic factors were identified by multivariable analysis in the training data set and used to construct a nomogram. After bootstraps internal and external validation, the predictive performance was evaluated by concordance index (C-index), Brier Score, and calibration curves. Risk group stratification was conducted using the score calculated by the nomogram. Then a simplified scoring system was built to make risk group stratification more convenient. RESULTS In total, 148 patients (training data set: n = 112; external validation data set: n = 36) were enrolled for analysis. Six potential predictors were identified and entered into the nomogram, including weight loss, histology, clinical TNM stage, clinical N category, tumor location, and tumor size. The C-indexes were 0.77 (95% CI, 0.65-0.88, internal validation) and 0.64 (95% CI, 0.43-0.85, external validation). The survival curves of different risk groups also displayed significant distinction (p < 0.0001). CONCLUSIONS We found weight loss, histology, clinical TNM stage, clinical N category, tumor location, and tumor size were prognostic factors of progression after receiving MWA plus chemotherapy and constructed a prediction model that can predict PFS. CLINICAL RELEVANCE STATEMENT The nomogram and scoring system will assist physicians to predict the individualized PFS of their patients and decide whether to perform or terminate MWA and chemotherapy according to the expected benefits. KEY POINTS • Build and validate a prognostic model using the data from a previous randomized controlled trial to predict progression-free survival after receiving MWA plus chemotherapy. • Weight loss, histology, clinical TNM stage, clinical N category, tumor location, and tumor size were prognostic factors. • The nomogram and scoring system published by the prediction model can be used to assist physicians to make clinical decisions.
Collapse
Affiliation(s)
- Fanhao Kong
- The First Clinical Department, China Medical University, 155 Nanjingbei Road, Liaoning Province, Shenyang, China.
| | - Honglan Yang
- Department of Oncology, Dongying People's Hospital, 317 Nanyi Road, Dongying, Shandong Province, China
| | - Qiaoxia Wang
- Department of Respiratory, Dongying People's Hospital, 317 Nanyi Road, Shandong Province, Dongying, China
| | - Zhigang Wei
- Department of Oncology, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Shandong Lung Cancer Institute, Shandong Key Laboratory of Rheumatic Disease and Translational Medicine, Jinan, Shandong Province, China.
- Cheeloo College of Medicine, Shandong University, Jinan, Shandong Province, China.
| | - Xin Ye
- Department of Oncology, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Shandong Lung Cancer Institute, Shandong Key Laboratory of Rheumatic Disease and Translational Medicine, Jinan, Shandong Province, China.
| |
Collapse
|
30
|
Ashfaq A, Gray GM, Carapelluci J, Amankwah EK, Rehman M, Puchalski M, Smith A, Quintessenza JA, Laks J, Ahumada LM, Asante-Korang A. Survival analysis for pediatric heart transplant patients using a novel machine learning algorithm: A UNOS analysis. J Heart Lung Transplant 2023; 42:1341-1348. [PMID: 37327979 DOI: 10.1016/j.healun.2023.06.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2023] [Revised: 05/22/2023] [Accepted: 06/09/2023] [Indexed: 06/18/2023] Open
Abstract
BACKGROUND Impact of pretransplantation risk factors on mortality in the first year after heart transplantation remains largely unknown. Using machine learning algorithms, we selected clinically relevant identifiers that could predict 1-year mortality after pediatric heart transplantation. METHODS Data were obtained from the United Network for Organ Sharing Database for years 2010-2020 for patients 0-17 years receiving their first heart transplant (N = 4150). Features were selected using subject experts and literature review. Scikit-Learn, Scikit-Survival, and Tensorflow were used. A train:test split of 70:30 was used. N-repeated k-fold validation was performed (N = 5, k = 5). Seven models were tested, Hyperparameter tuning performed using Bayesian optimization and the concordance index (C-index) was used for model assessment. RESULTS A C-index above 0.6 for test data was considered acceptable for survival analysis models. C-indices obtained were 0.60 (Cox proportional hazards), 0.61 (Cox with elastic net), 0.64 (gradient boosting), 0.64 (support vector machine), 0.68 (random forest), 0.66 (component gradient boosting), and 0.54 (survival trees). Machine learning models show an improvement over the traditional Cox proportional hazards model, with random forest performing the best on the test set. Analysis of the feature importance for the gradient boosted model found that the top 5 features were the most recent serum total bilirubin, the travel distance from the transplant center, the patient body mass index, the deceased donor terminal Serum glutamic pyruvic transaminase/Alanine transaminase (SGPT/ALT), and the donor PCO2. CONCLUSIONS Combination of machine learning and expert-based methodology of selecting predictors of survival for pediatric heart transplantation provides a reasonable prediction of 1- and 3-year survival outcomes. SHapley Additive exPlanations can be an effective tool for modeling and visualizing nonlinear interactions.
Collapse
Affiliation(s)
- Awais Ashfaq
- From the Cardiovascular Surgery, Heart Institute, Johns Hopkins All Children's Hospital, St. Petersburg, Florida.
| | - Geoffrey M Gray
- Center for Pediatric Data Science and Analytic Methodology, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| | - Jennifer Carapelluci
- Heart Transplantation, Cardiomyopathy and Heart Failure, Heart Institute, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| | - Ernest K Amankwah
- Epidemiology and Biostatistics, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| | - Mohamed Rehman
- From the Cardiovascular Surgery, Heart Institute, Johns Hopkins All Children's Hospital, St. Petersburg, Florida; Department of Anesthesia and Pain Medicine, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| | - Michael Puchalski
- Division of Cardiology, Heart Institute, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| | - Andrew Smith
- and the Division of Cardiac Critical Care, Heart Institute, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| | - James A Quintessenza
- From the Cardiovascular Surgery, Heart Institute, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| | - Jessica Laks
- Heart Transplantation, Cardiomyopathy and Heart Failure, Heart Institute, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| | - Luis M Ahumada
- Center for Pediatric Data Science and Analytic Methodology, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| | - Alfred Asante-Korang
- Heart Transplantation, Cardiomyopathy and Heart Failure, Heart Institute, Johns Hopkins All Children's Hospital, St. Petersburg, Florida
| |
Collapse
|
31
|
Galetzka W, Kowall B, Jusi C, Huessler EM, Stang A. Distance-Metric Learning for Personalized Survival Analysis. ENTROPY (BASEL, SWITZERLAND) 2023; 25:1404. [PMID: 37895525 PMCID: PMC10606222 DOI: 10.3390/e25101404] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/13/2023] [Revised: 09/21/2023] [Accepted: 09/26/2023] [Indexed: 10/29/2023]
Abstract
Personalized time-to-event or survival prediction with right-censored outcomes is a pervasive challenge in healthcare research. Although various supervised machine learning methods, such as random survival forests or neural networks, have been adapted to handle such outcomes effectively, they do not provide explanations for their predictions, lacking interpretability. In this paper, an alternative method for survival prediction by weighted nearest neighbors is proposed. Fitting this model to data entails optimizing the weights by learning a metric. An individual prediction of this method can be explained by providing the user with the most influential data points for this prediction, i.e., the closest data points and their weights. The strengths and weaknesses in terms of predictive performance are highlighted on simulated data and an application of the method on two different real-world datasets of breast cancer patients shows its competitiveness with established methods.
Collapse
Affiliation(s)
- Wolfgang Galetzka
- Institute of Medical Informatics, Biometrics and Epidemiology, University Hospital Essen, 45130 Essen, Germany
| | - Bernd Kowall
- Institute of Medical Informatics, Biometrics and Epidemiology, University Hospital Essen, 45130 Essen, Germany
| | - Cynthia Jusi
- Nisso Chemical Europe GmbH, 40212 Düsseldorf, Germany
| | - Eva-Maria Huessler
- Institute of Medical Informatics, Biometrics and Epidemiology, University Hospital Essen, 45130 Essen, Germany
| | - Andreas Stang
- Institute of Medical Informatics, Biometrics and Epidemiology, University Hospital Essen, 45130 Essen, Germany
| |
Collapse
|
32
|
Höhn J, Krieghoff-Henning E, Wies C, Kiehl L, Hetz MJ, Bucher TC, Jonnagaddala J, Zatloukal K, Müller H, Plass M, Jungwirth E, Gaiser T, Steeg M, Holland-Letz T, Brenner H, Hoffmeister M, Brinker TJ. Colorectal cancer risk stratification on histological slides based on survival curves predicted by deep learning. NPJ Precis Oncol 2023; 7:98. [PMID: 37752266 PMCID: PMC10522577 DOI: 10.1038/s41698-023-00451-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Accepted: 09/06/2023] [Indexed: 09/28/2023] Open
Abstract
Studies have shown that colorectal cancer prognosis can be predicted by deep learning-based analysis of histological tissue sections of the primary tumor. So far, this has been achieved using a binary prediction. Survival curves might contain more detailed information and thus enable a more fine-grained risk prediction. Therefore, we established survival curve-based CRC survival predictors and benchmarked them against standard binary survival predictors, comparing their performance extensively on the clinical high and low risk subsets of one internal and three external cohorts. Survival curve-based risk prediction achieved a very similar risk stratification to binary risk prediction for this task. Exchanging other components of the pipeline, namely input tissue and feature extractor, had largely identical effects on model performance independently of the type of risk prediction. An ensemble of all survival curve-based models exhibited a more robust performance, as did a similar ensemble based on binary risk prediction. Patients could be further stratified within clinical risk groups. However, performance still varied across cohorts, indicating limited generalization of all investigated image analysis pipelines, whereas models using clinical data performed robustly on all cohorts.
Collapse
Affiliation(s)
- Julia Höhn
- Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Eva Krieghoff-Henning
- Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Christoph Wies
- Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Medical Faculty, University Heidelberg, Heidelberg, Germany
| | - Lennard Kiehl
- Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Martin J Hetz
- Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Tabea-Clara Bucher
- Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Jitendra Jonnagaddala
- School of Population Health, Faculty of Medicine and Health, UNSW Sydney, Kensington, NSW, Australia
| | - Kurt Zatloukal
- Diagnostic and Research Center for Molecular BioMedicine, Diagnostic & Research Institute of Pathology, Medical University of Graz, Graz, Austria
| | - Heimo Müller
- Diagnostic and Research Center for Molecular BioMedicine, Diagnostic & Research Institute of Pathology, Medical University of Graz, Graz, Austria
| | - Markus Plass
- Diagnostic and Research Center for Molecular BioMedicine, Diagnostic & Research Institute of Pathology, Medical University of Graz, Graz, Austria
| | - Emilian Jungwirth
- Diagnostic and Research Center for Molecular BioMedicine, Diagnostic & Research Institute of Pathology, Medical University of Graz, Graz, Austria
| | - Timo Gaiser
- Institute of Pathology, University Medical Center Mannheim, University of Heidelberg, Mannheim, Germany
- Institute of Applied Pathology, Speyer, Germany
| | - Matthias Steeg
- Institute of Pathology, University Medical Center Mannheim, University of Heidelberg, Mannheim, Germany
| | - Tim Holland-Letz
- Department of Biostatistics, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Hermann Brenner
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Division of Preventive Oncology, German Cancer Research Center (DKFZ) and National Center for Tumor Diseases (NCT), Heidelberg, Germany
- German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Michael Hoffmeister
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Titus J Brinker
- Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany.
| |
Collapse
|
33
|
Kim SY. GNN-surv: Discrete-Time Survival Prediction Using Graph Neural Networks. Bioengineering (Basel) 2023; 10:1046. [PMID: 37760148 PMCID: PMC10525217 DOI: 10.3390/bioengineering10091046] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Revised: 08/31/2023] [Accepted: 09/04/2023] [Indexed: 09/29/2023] Open
Abstract
Survival prediction models play a key role in patient prognosis and personalized treatment. However, their accuracy can be improved by incorporating patient similarity networks, which uncover complex data patterns. Our study uses Graph Neural Networks (GNNs) to enhance discrete-time survival predictions (GNN-surv) by leveraging relationships in these networks. We build these networks using cancer patients' genomic and clinical data and train various GNN models on them, integrating Logistic Hazard and PMF survival models. GNN-surv models exhibit superior performance in survival prediction across two urologic cancer datasets, outperforming traditional MLP models. They maintain robustness and effectiveness under varying graph construction hyperparameter μ values, with performance boosts of up to 14.6% and 7.9% in the time-dependent concordance index and reductions in the integrated brier score of 26.7% and 24.1% in the BLCA and KIRC datasets, respectively. Notably, these models also maintain their effectiveness across three different types of GNN models, suggesting potential adaptability to other cancer datasets. The superior performance of our GNN-surv models underscores their wide applicability in the fields of oncology and personalized medicine, providing clinicians with a more accurate tool for patient prognosis and personalized treatment planning. Future studies can further optimize these models by incorporating other survival models or additional data modalities.
Collapse
Affiliation(s)
- So Yeon Kim
- Department of Artificial Intelligence, Ajou University, Suwon 16499, Republic of Korea;
- Department of Software and Computer Engineering, Ajou University, Suwon 16499, Republic of Korea
| |
Collapse
|
34
|
Zou H, Zeng D, Xiao L, Luo S. BAYESIAN INFERENCE AND DYNAMIC PREDICTION FOR MULTIVARIATE LONGITUDINAL AND SURVIVAL DATA. Ann Appl Stat 2023; 17:2574-2595. [PMID: 37719893 PMCID: PMC10500582 DOI: 10.1214/23-aoas1733] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/19/2023]
Abstract
Alzheimer's disease (AD) is a complex neurological disorder impairing multiple domains such as cognition and daily functions. To better understand the disease and its progression, many AD research studies collect multiple longitudinal outcomes that are strongly predictive of the onset of AD dementia. We propose a joint model based on a multivariate functional mixed model framework (referred to as MFMM-JM) that simultaneously models the multiple longitudinal outcomes and the time to dementia onset. We develop six functional forms to fully investigate the complex association between longitudinal outcomes and dementia onset. Moreover, we use the Bayesian methods for statistical inference and develop a dynamic prediction framework that provides accurate personalized predictions of disease progressions based on new subject-specific data. We apply the proposed MFMM-JM to two large ongoing AD studies: the Alzheimer's Disease Neuroimaging Initiative (ADNI) and National Alzheimer's Coordinating Center (NACC), and identify the functional forms with the best predictive performance. our method is also validated by extensive simulation studies with five settings.
Collapse
Affiliation(s)
- Haotian Zou
- Department of Biostatistics, University of North Carolina at Chapel Hill
| | - Donglin Zeng
- Department of Biostatistics, University of North Carolina at Chapel Hill
| | - Luo Xiao
- Department of Statistics, North Carolina State University
| | - Sheng Luo
- Department of Biostatistics and Bioinformatics, Duke University
| |
Collapse
|
35
|
Liang M, Li Z, Li L, Chinchilli VM, Zhang L, Wang M. Tackling dynamic prediction of death in patients with recurrent cardiovascular events. Stat Med 2023; 42:3487-3507. [PMID: 37282984 DOI: 10.1002/sim.9815] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2022] [Revised: 04/03/2023] [Accepted: 05/18/2023] [Indexed: 06/08/2023]
Abstract
In the field of cardiovascular disease, recurrent events such as stroke or myocardial infarction (MI) are often encountered, leading to an increase in the risk of death. Accurately evaluating the prognosis of patients and dynamically predicting the risk of death by considering the historical recurrent events can improve medical decisions and lead to better health care outcomes. Recently proposed joint modeling approaches within the Bayesian framework have inspired the development of a dynamic prediction tool, which can be applied for subject-level prediction of death with implementation in software packages. The prediction model incorporates subject heterogeneity with subject-level random effects that account for unobserved time-invariant factors and an extra copula function capturing the part caused by unmeasured time-dependent factors. Thereafter, given the prespecified landmark timet ' $$ {t}^{\prime } $$ , the survival probability for a prediction horizon time of interestt $$ t $$ can be estimated for each individual. The prediction accuracy is assessed by time-dependent receiving operating characteristic curve and the area under the curve and the Brier score with calibration plots is compared to traditional joint frailty models. Finally, the tool is applied to patients with multiple attacks of stroke or MI in the Cardiovascular Health study and the Atherosclerosis Risk in Communities study for illustration.
Collapse
Affiliation(s)
- Menglu Liang
- Division of Biostatistics and Bioinformatics, Department of Public Health Sciences, Penn State College of Medicine, Hershey, Pennsylvania, USA
| | - Zheng Li
- Novartis Pharmaceuticals, East Hanover, New Jersey, USA
| | - Liang Li
- Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Vernon M Chinchilli
- Division of Biostatistics and Bioinformatics, Department of Public Health Sciences, Penn State College of Medicine, Hershey, Pennsylvania, USA
| | - Lijun Zhang
- Department of Population and Quantitative Health Sciences, School of Medicine, Case Western Reserve University, Cleaveland, OH, USA
| | - Ming Wang
- Department of Population and Quantitative Health Sciences, School of Medicine, Case Western Reserve University, Cleaveland, OH, USA
| |
Collapse
|
36
|
Kim J, Lee S, Kim JH, Im DW, Lee D, Oh KH. Comparing predictions among competing risks models with rare events: application to KNOW-CKD atudy-a multicentre cohort study of chronic kidney disease. Sci Rep 2023; 13:13315. [PMID: 37587215 PMCID: PMC10432513 DOI: 10.1038/s41598-023-40570-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2023] [Accepted: 08/13/2023] [Indexed: 08/18/2023] Open
Abstract
A prognostic model to determine an association between survival outcomes and clinical risk factors, such as the Cox model, has been developed over the past decades in the medical field. Although the data size containing subjects' information gradually increases, the number of events is often relatively low as medical technology develops. Accordingly, poor discrimination and low predicted ability may occur between low- and high-risk groups. The main goal of this study was to evaluate the predicted probabilities with three existing competing risks models in variation with censoring rates. Three methods were illustrated and compared in a longitudinal study of a nationwide prospective cohort of patients with chronic kidney disease in Korea. The prediction accuracy and discrimination ability of the three methods were compared in terms of the Concordance index (C-index), Integrated Brier Score (IBS), and Calibration slope. In addition, we find that these methods have different performances when the effects are linear or nonlinear under various censoring rates.
Collapse
Affiliation(s)
- Jayoun Kim
- Medical Research Collaborating Center, Seoul National University Hospital, Seoul, Republic of Korea
| | - Soohyeon Lee
- Department of Statistics, Ewha Womans University, Seoul, Republic of Korea
| | - Ji Hye Kim
- Department of Internal Medicine, Chungbuk National University Hospital, Cheongju, Korea
| | - Dha Woon Im
- Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea
| | - Donghwan Lee
- Department of Statistics, Ewha Womans University, Seoul, Republic of Korea.
| | - Kook-Hwan Oh
- Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
| |
Collapse
|
37
|
Sun J, Li F, Yang J, Lin C, Zhou X, Liu N, Zhang B, Song G, Wang W, Huang C, Song Z, Shi L. Pretherapy investigations using highly robust visualized biomarkers from CT imaging by multiple machine-learning techniques toward its prognosis prediction for ALK-inhibitor therapy in NSCLC: a feasibility study. J Cancer Res Clin Oncol 2023; 149:7341-7353. [PMID: 36928998 DOI: 10.1007/s00432-023-04615-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2022] [Accepted: 01/27/2023] [Indexed: 03/18/2023]
Abstract
PURPOSE Molecularly targeted therapy has revolutionized the therapeutic landscape and is emerging as the first-line treatment option for ALK-rearranged non-small-cell lung cancer (NSCLC). In this study, the highly informative and robust biomarkers based on pre-treatment CT images and clinicopathologic features will be developed and validated to predict the prognosis for ALK-inhibitor therapy in NSCLC patients. METHODS A total of 161 ALK-positive NSCLC patients treated with ALK inhibitors were retrospectively collected as training, validation and test sets from multi-center institutions. Cox proportional hazard regression (CPH) penalized by LASSO and random survival forest (RSF) coupled with recursive feature elimination (RFE) were used for radiomics and clinical features identification and model construction. An overlapping post-processing method was extra added to training process to investigate the stronger biomarker on the whole set. RESULTS 123 of the collected cases progressed after a median follow-up of 15.5 months (IQR, 8.3-25.3). The T and M staging, pericardial effusion, age and ALK inhibitor-alectinib were determined as significant predictors in the survival analysis. Furthermore, we visualized the finally retained 4 radiomics feature. The RSF models built from overlapping-processed clinical and radiomics features respectively reached the maximum C-index of 0.68 and 0.75,but the combination of them,radioclinical signature, improved the score to 0.78. The model on the validation and external test datasets yielded the C-index of 0.73 and 0.79, with the iAUC of 0.76 and 0.83, the IBS of 0.119 and 0.112. CONCLUSION With respect to a simple selection strategy of overlapping optimal radiomics and clinical features from different survival models may promote better progression-free survival(PFS) prediction than conventional survival analysis, which provides a potential method for guiding personalized pre-treatment options of NSCLC.
Collapse
Affiliation(s)
- Jingjing Sun
- Department of Radiology, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Feng Li
- Department of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co, Ltd, Beijing, 100080, China
| | - Jiantao Yang
- Department of Radiology, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Chen Lin
- Department of Radiology, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Xianglan Zhou
- Department of Radiology, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Na Liu
- Department of Radiology, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Bingqian Zhang
- Department of Radiology, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Ge Song
- Department of Radiology, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Wenxian Wang
- Department of Medical Oncology, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Chencui Huang
- Department of Research Collaboration, R&D Center, Beijing Deepwise & League of PHD Technology Co, Ltd, Beijing, 100080, China
| | - Zhengbo Song
- Department of Clinical Trial, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China.
| | - Lei Shi
- Department of Radiology, Zhejiang Cancer Hospital, Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China.
| |
Collapse
|
38
|
Zheng Y, Carrillo-Perez F, Pizurica M, Heiland DH, Gevaert O. Spatial cellular architecture predicts prognosis in glioblastoma. Nat Commun 2023; 14:4122. [PMID: 37433817 DOI: 10.1038/s41467-023-39933-0] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2023] [Accepted: 06/30/2023] [Indexed: 07/13/2023] Open
Abstract
Intra-tumoral heterogeneity and cell-state plasticity are key drivers for the therapeutic resistance of glioblastoma. Here, we investigate the association between spatial cellular organization and glioblastoma prognosis. Leveraging single-cell RNA-seq and spatial transcriptomics data, we develop a deep learning model to predict transcriptional subtypes of glioblastoma cells from histology images. Employing this model, we phenotypically analyze 40 million tissue spots from 410 patients and identify consistent associations between tumor architecture and prognosis across two independent cohorts. Patients with poor prognosis exhibit higher proportions of tumor cells expressing a hypoxia-induced transcriptional program. Furthermore, a clustering pattern of astrocyte-like tumor cells is associated with worse prognosis, while dispersion and connection of the astrocytes with other transcriptional subtypes correlate with decreased risk. To validate these results, we develop a separate deep learning model that utilizes histology images to predict prognosis. Applying this model to spatial transcriptomics data reveal survival-associated regional gene expression programs. Overall, our study presents a scalable approach to unravel the transcriptional heterogeneity of glioblastoma and establishes a critical connection between spatial cellular architecture and clinical outcomes.
Collapse
Affiliation(s)
- Yuanning Zheng
- Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, CA, 94305, USA
| | - Francisco Carrillo-Perez
- Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, CA, 94305, USA
- Department of Architecture and Computer Technology (ATC), University of Granada, Granada, 18014, Spain
| | - Marija Pizurica
- Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, CA, 94305, USA
- Internet technology and Data science Lab (IDLab), Ghent University, Technologiepark-Zwijnaarde 126, Ghent, 9052, Gent, Belgium
| | - Dieter Henrik Heiland
- Microenvironment and Immunology Research Laboratory, Medical Center, University of Freiburg, Freiburg, 79106, Germany
- Department of Neurosurgery, Medical Center, University of Freiburg, Freiburg, 79106, Germany
| | - Olivier Gevaert
- Department of Medicine, Stanford Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, CA, 94305, USA.
- Department of Biomedical Data Science, Stanford University, Stanford, CA, 94305, USA.
| |
Collapse
|
39
|
Ghanem M, Ghaith AK, Zamanian C, Bon-Nieves A, Bhandarkar A, Bydon M, Quiñones-Hinojosa A. Deep Learning Approaches for Glioblastoma Prognosis in Resource-Limited Settings: A Study Using Basic Patient Demographic, Clinical, and Surgical Inputs. World Neurosurg 2023; 175:e1089-e1109. [PMID: 37088416 DOI: 10.1016/j.wneu.2023.04.072] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2023] [Revised: 04/15/2023] [Accepted: 04/17/2023] [Indexed: 04/25/2023]
Abstract
BACKGROUND Glioblastoma (GBM) is the most common brain tumor in the United States, with an annual incidence rate of 3.21 per 100,000. It is the most aggressive type of diffuse glioma and has a median survival of months after treatment. This study aims to assess the accuracy of different novel deep learning models trained on a set of simple clinical, demographic, and surgical variables to assist in clinical practice, even in areas with constrained health care infrastructure. METHODS Our study included 37,095 patients with GBM from the SEER (Surveillance Epidemiology and End Results) database. All predictors were based on demographic, clinicopathologic, and treatment information of the cases. Our outcomes of interest were months of survival and vital status. Concordance index (C-index) and integrated Brier scores (IBS) were used to evaluate the performance of the models. RESULTS The patient characteristics and the statistical analyses were consistent with the epidemiologic literature. The models C-index and IBS ranged from 0.6743 to 0.6918 and from 0.0934 to 0.1034, respectively. Probabilistic matrix factorization (0.6918), multitask logistic regression (0.6916), and logistic hazard (0.6916) had the highest C-index scores. The models with the lowest IBS were the probabilistic matrix factorization (0.0934), multitask logistic regression (0.0935), and logistic hazard (0.0936). These models had an accuracy (1-IBS) of 90.66%; 90.65%, and 90.64%, respectively. The deep learning algorithms were deployed on an interactive Web-based tool for practical use available via https://glioblastoma-survanalysis.herokuapp.com/. CONCLUSIONS Novel deep learning algorithms can better predict GBM prognosis than do baseline methods and can lead to more personalized patient care regardless of extensive electronic health record availability.
Collapse
Affiliation(s)
- Marc Ghanem
- Gilbert and Rose-Marie Chagoury School of Medicine, Lebanese American University, Beirut, Lebanon
| | - Abdul Karim Ghaith
- Mayo Clinic Neuro-Informatics Laboratory, Mayo Clinic, Rochester, Minnesota, USA; Department of Neurological Surgery, Mayo Clinic, Rochester, Minnesota, USA
| | - Cameron Zamanian
- Mayo Clinic Neuro-Informatics Laboratory, Mayo Clinic, Rochester, Minnesota, USA; Department of Neurological Surgery, Mayo Clinic, Rochester, Minnesota, USA
| | - Antonio Bon-Nieves
- Mayo Clinic Neuro-Informatics Laboratory, Mayo Clinic, Rochester, Minnesota, USA; Department of Neurological Surgery, Mayo Clinic, Rochester, Minnesota, USA
| | - Archis Bhandarkar
- Mayo Clinic Neuro-Informatics Laboratory, Mayo Clinic, Rochester, Minnesota, USA; Department of Neurological Surgery, Mayo Clinic, Rochester, Minnesota, USA
| | - Mohamad Bydon
- Mayo Clinic Neuro-Informatics Laboratory, Mayo Clinic, Rochester, Minnesota, USA; Department of Neurological Surgery, Mayo Clinic, Rochester, Minnesota, USA.
| | | |
Collapse
|
40
|
Yuan T, Chen X, Zhang Y, Wei M, Zhu H, Yang Z, Wang X. A novel prognostic index for diffuse large B-cell lymphoma combined baseline metabolic tumour volume with clinical and pathological risk factors. Nucl Med Commun 2023; 44:622-630. [PMID: 37114393 DOI: 10.1097/mnm.0000000000001701] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/29/2023]
Abstract
OBJECTIVES This study aimed to develop a novel prognostic index integrating baseline metabolic tumour volume (MTV) along with clinical and pathological parameters for diffuse large B-cell lymphoma (DLBCL). METHODS This prospective trial enrolled 289 patients with newly diagnosed DLBCL. The predictive value of novel prognostic index was compared with Ann Arbor staging and National Comprehensive Cancer Network International Prognostic Index (NCCN-IPI). We used the concordance index (C-index) and a calibration curve to determine its predictive capacity. RESULTS Multivariate analysis revealed high MTV (>191 cm 3 ), Ann Arbor stage (III-IV) and MYC/BCL2 double expression lymphoma (DEL) to be independently associated with inferior progression-free survival (PFS) and overall survival (OS). Ann Arbor stage and DEL could be stratified by MTV. Our index, combining MTV with Ann Arbor stage and DEL status, identified four prognostic groups: group 1 (no risk factors,), group 2 (one risk factor), group 3 (two risk factors), and group 4 (three risk factors). The 2-year PFS rates were 85.5, 73.9, 53.6, and 13.9%; 2-year OS rates were 94.6, 87.0, 67.5, and 24.2%, respectively. The C-index values of the novel index were 0.697 and 0.753 for PFS and OS prediction, which was superior to Ann Arbor stage and NCCN-IPI. CONCLUSION The novel index including tumour burden and clinicopathological features may help predict outcome of DLBCL (clinicaltrials.gov identifier: NCT02928861).
Collapse
Affiliation(s)
- Tingting Yuan
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), NMPA Key Laboratory for Research and Evaluation of Radiopharmaceuticals (National Medical Products Administration), Department of Nuclear Medicine, Peking University Cancer Hospital & Institute
- Department of Nuclear Medicine, Peking University International Hospital, Beijing, China
| | - Xuetao Chen
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), NMPA Key Laboratory for Research and Evaluation of Radiopharmaceuticals (National Medical Products Administration), Department of Nuclear Medicine, Peking University Cancer Hospital & Institute
| | - Yuewei Zhang
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), NMPA Key Laboratory for Research and Evaluation of Radiopharmaceuticals (National Medical Products Administration), Department of Nuclear Medicine, Peking University Cancer Hospital & Institute
| | - Maomao Wei
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), NMPA Key Laboratory for Research and Evaluation of Radiopharmaceuticals (National Medical Products Administration), Department of Nuclear Medicine, Peking University Cancer Hospital & Institute
| | - Hua Zhu
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), NMPA Key Laboratory for Research and Evaluation of Radiopharmaceuticals (National Medical Products Administration), Department of Nuclear Medicine, Peking University Cancer Hospital & Institute
| | - Zhi Yang
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), NMPA Key Laboratory for Research and Evaluation of Radiopharmaceuticals (National Medical Products Administration), Department of Nuclear Medicine, Peking University Cancer Hospital & Institute
| | - Xuejuan Wang
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), NMPA Key Laboratory for Research and Evaluation of Radiopharmaceuticals (National Medical Products Administration), Department of Nuclear Medicine, Peking University Cancer Hospital & Institute
| |
Collapse
|
41
|
Zarean Shahraki S, Azizmohammad Looha M, Mohammadi kazaj P, Aria M, Akbari A, Emami H, Asadi F, Akbari ME. Time-related survival prediction in molecular subtypes of breast cancer using time-to-event deep-learning-based models. Front Oncol 2023; 13:1147604. [PMID: 37342184 PMCID: PMC10277681 DOI: 10.3389/fonc.2023.1147604] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2023] [Accepted: 05/19/2023] [Indexed: 06/22/2023] Open
Abstract
Background Breast cancer (BC) survival prediction can be a helpful tool for identifying important factors selecting the effective treatment reducing mortality rates. This study aims to predict the time-related survival probability of BC patients in different molecular subtypes over 30 years of follow-up. Materials and methods This study retrospectively analyzed 3580 patients diagnosed with invasive breast cancer (BC) from 1991 to 2021 in the Cancer Research Center of Shahid Beheshti University of Medical Science. The dataset contained 18 predictor variables and two dependent variables, which referred to the survival status of patients and the time patients survived from diagnosis. Feature importance was performed using the random forest algorithm to identify significant prognostic factors. Time-to-event deep-learning-based models, including Nnet-survival, DeepHit, DeepSurve, NMLTR and Cox-time, were developed using a grid search approach with all variables initially and then with only the most important variables selected from feature importance. The performance metrics used to determine the best-performing model were C-index and IBS. Additionally, the dataset was clustered based on molecular receptor status (i.e., luminal A, luminal B, HER2-enriched, and triple-negative), and the best-performing prediction model was used to estimate survival probability for each molecular subtype. Results The random forest method identified tumor state, age at diagnosis, and lymph node status as the best subset of variables for predicting breast cancer (BC) survival probabilities. All models yielded very close performance, with Nnet-survival (C-index=0.77, IBS=0.13) slightly higher using all 18 variables or the three most important variables. The results showed that the Luminal A had the highest predicted BC survival probabilities, while triple-negative and HER2-enriched had the lowest predicted survival probabilities over time. Additionally, the luminal B subtype followed a similar trend as luminal A for the first five years, after which the predicted survival probability decreased steadily in 10- and 15-year intervals. Conclusion This study provides valuable insight into the survival probability of patients based on their molecular receptor status, particularly for HER2-positive patients. This information can be used by healthcare providers to make informed decisions regarding the appropriateness of medical interventions for high-risk patients. Future clinical trials should further explore the response of different molecular subtypes to treatment in order to optimize the efficacy of breast cancer treatments.
Collapse
Affiliation(s)
- Saba Zarean Shahraki
- Department of Health Information Technology and Management, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Mehdi Azizmohammad Looha
- Basic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Pooya Mohammadi kazaj
- Geographic Information Systems Department, Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, Iran
| | - Mehrad Aria
- Faculty of Information Technology and Computer Engineering, Azarbaijan Shahid Madani University, Tehran, Iran
| | - Atieh Akbari
- Cancer Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Hassan Emami
- Department of Health Information Technology and Management, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Farkhondeh Asadi
- Department of Health Information Technology and Management, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | | |
Collapse
|
42
|
Kong J, Zhang S. Buckley-James boosting model based on extreme learning machine and random survival forests. Biom J 2023; 65:e2200153. [PMID: 37068191 DOI: 10.1002/bimj.202200153] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2022] [Revised: 12/15/2022] [Accepted: 03/10/2023] [Indexed: 04/19/2023]
Abstract
Buckley-James (BJ) model is a typical semiparametric accelerated failure time model, which is closely related to the ordinary least squares method and easy to be constructed. However, traditional BJ model built on linearity assumption only captures simple linear relationships, while it has difficulty in processing nonlinear problems. To overcome this difficulty, in this paper, we develop a novel regression model for right-censored survival data within the learning framework of BJ model, basing on random survival forests (RSF), extreme learning machine (ELM), and L2 boosting algorithm. The proposed method, referred to as ELM-based BJ boosting model, employs RSF for covariates imputation first, then develops a new ensemble of ELMs-ELM-based boosting algorithm for regression by ensemble scheme of L2 boosting, and finally, uses the output function of the proposed ELM-based boosting model to replace the linear combination of covariates in BJ model. Due to fitting the logarithm of survival time with covariates by the nonparametric ELM-based boosting method instead of the least square method, the ELM-based BJ boosting model can capture both linear covariate effects and nonlinear covariate effects. In both simulation studies and real data applications, in terms of concordance index and integrated Brier sore, the proposed ELM-based BJ boosting model can outperform traditional BJ model, two kinds of BJ boosting models proposed by Wang et al., RSF, and Cox proportional hazards model.
Collapse
Affiliation(s)
- Jianfen Kong
- School of Mathematics and Statistics, Center for Data Science, Lanzhou University, Lanzhou, P.R.China
| | - Shuhong Zhang
- School of Mathematics and Statistics, Center for Data Science, Lanzhou University, Lanzhou, P.R.China
| |
Collapse
|
43
|
Jiang S, Cao J, Rosner B, Colditz GA. Supervised two-dimensional functional principal component analysis with time-to-event outcomes and mammogram imaging data. Biometrics 2023; 79:1359-1369. [PMID: 34854477 PMCID: PMC9160217 DOI: 10.1111/biom.13611] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2021] [Revised: 11/07/2021] [Accepted: 11/15/2021] [Indexed: 12/24/2022]
Abstract
Screening mammography aims to identify breast cancer early and secondarily measures breast density to classify women at higher or lower than average risk for future breast cancer in the general population. Despite the strong association of individual mammography features to breast cancer risk, the statistical literature on mammogram imaging data is limited. While functional principal component analysis (FPCA) has been studied in the literature for extracting image-based features, it is conducted independently of the time-to-event response variable. With the consideration of building a prognostic model for precision prevention, we present a set of flexible methods, supervised FPCA (sFPCA) and functional partial least squares (FPLS), to extract image-based features associated with the failure time while accommodating the added complication from right censoring. Throughout the article, we hope to demonstrate that one method is favored over the other under different clinical setups. The proposed methods are applied to the motivating data set from the Joanne Knight Breast Health cohort at Siteman Cancer Center. Our approaches not only obtain the best prediction performance compared to the benchmark model, but also reveal different risk patterns within the mammograms.
Collapse
Affiliation(s)
- Shu Jiang
- Division of Public Health Sciences, Washington University School of Medicine in St. Louis, Missouri
| | - Jiguo Cao
- Department of Statistics and Actuarial Science, Simon Fraser University, Canada
| | - Bernard Rosner
- Channing Division of Network Medicine, Harvard Medical School, Massachusetts
| | - Graham A Colditz
- Division of Public Health Sciences, Washington University School of Medicine in St. Louis, Missouri
| |
Collapse
|
44
|
Wang M, Chekouo T, Ismail Z, Forkert ND, Hogan DB, Ganesh A, Camicioli R, Seitz D, Borrie MJ, Hsiung GYR, Masellis M, Moorhouse P, Tartaglia C, Smith EE, Sajobi TT. Elicited clinician knowledge did not improve dementia risk prediction in individuals with mild cognitive impairment. J Clin Epidemiol 2023; 158:111-118. [PMID: 36931477 DOI: 10.1016/j.jclinepi.2023.03.009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Revised: 03/10/2023] [Accepted: 03/13/2023] [Indexed: 03/17/2023]
Abstract
OBJECTIVES This study aims to develop and validate a Bayesian risk prediction model that combines research cohort data with elicited expert knowledge to predict dementia progression in people with mild cognitive impairment (MCI). STUDY DESIGN AND SETTING This is a prognostic risk prediction modeling study based on cohort data (Alzheimer's disease neuroimaging initiative [ADNI]; n = 365) of research participants with MCI and elicited expert data. Bayesian Cox models were used to combine expert knowledge and ADNI data to predict dementia progression in people with MCI. Posterior distributions were obtained based on Gibbs sampler and the predictive performance was evaluated using ten-fold cross-validation via c-index, integrated calibration index (ICI), and integrated brier score (IBS). RESULTS 365 people with MCI were included, mean age was 73 years (SD = 7.5), and 39% developed dementia within 3 years. When expert knowledge was incorporated, the c-index, ICI, and IBS values were 0.74 (95% CI 0.70-0.79), 0.06 (95% CI 0.05-0.08), and 0.17 (95% CI 0.14-0.19), respectively. These were similar to the model without expert knowledge data. CONCLUSION The addition of expert knowledge did not improve model accuracy in this ADNI sample to predict dementia progression in individuals with MCI.
Collapse
Affiliation(s)
- Meng Wang
- Department of Community Health Sciences & O'Brien Institute of Public Health, University of Calgary, Canada; Department of Clinical Neurosciences & Hotchkiss Brain Institute, University of Calgary, Canada
| | - Thierry Chekouo
- Division of Biostatistics, School of Public Health, University of Minnesota, USA
| | - Zahinoor Ismail
- Department of Community Health Sciences & O'Brien Institute of Public Health, University of Calgary, Canada; Department of Clinical Neurosciences & Hotchkiss Brain Institute, University of Calgary, Canada; Department of Psychiatry, University of Calgary, Canada
| | - Nils D Forkert
- Department of Clinical Neurosciences & Hotchkiss Brain Institute, University of Calgary, Canada; Department of Radiology, University of Calgary, Canada
| | - David B Hogan
- Department of Community Health Sciences & O'Brien Institute of Public Health, University of Calgary, Canada; Department of Clinical Neurosciences & Hotchkiss Brain Institute, University of Calgary, Canada
| | - Aravind Ganesh
- Department of Clinical Neurosciences & Hotchkiss Brain Institute, University of Calgary, Canada
| | - Richard Camicioli
- Division of Neurology, Department of Medicine, University of Alberta, Canada
| | - Dallas Seitz
- Department of Psychiatry, University of Calgary, Canada
| | - Michael J Borrie
- Division of Geriatric Medicine, Department of Medicine, Western University, Canada
| | - Ging-Yuek Robin Hsiung
- Division of Neurology, Department of Medicine, The University of British Columbia, Canada
| | | | - Paige Moorhouse
- Division of Geriatric Medicine, Department of Medicine, Dalhousie University, Canada
| | - Carmela Tartaglia
- Tanz Centre for Research in Neurodegenerative Diseases, University of Toronto, Canada
| | - Eric E Smith
- Department of Clinical Neurosciences & Hotchkiss Brain Institute, University of Calgary, Canada
| | - Tolulope T Sajobi
- Department of Community Health Sciences & O'Brien Institute of Public Health, University of Calgary, Canada; Department of Clinical Neurosciences & Hotchkiss Brain Institute, University of Calgary, Canada.
| |
Collapse
|
45
|
Fan L, Bonomi L. Mitigating Membership Inference in Deep Survival Analyses with Differential Privacy. IEEE INTERNATIONAL CONFERENCE ON HEALTHCARE INFORMATICS. IEEE INTERNATIONAL CONFERENCE ON HEALTHCARE INFORMATICS 2023; 2023:81-90. [PMID: 38152589 PMCID: PMC10751041 DOI: 10.1109/ichi57859.2023.00022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/29/2023]
Abstract
Deep neural networks have been increasingly integrated in healthcare applications to enable accurate predicative analyses. Sharing trained deep models not only facilitates knowledge integration in collaborative research efforts but also enables equitable access to computational intelligence. However, recent studies have shown that an adversary may leverage a shared model to learn the participation of a target individual in the training set. In this work, we investigate privacy-protecting model sharing for survival studies. Specifically, we pose three research questions. (1) Do deep survival models leak membership information? (2) How effective is differential privacy in defending against membership inference in deep survival analyses? (3) Are there other effects of differential privacy on deep survival analyses? Our study assesses the membership leakage in emerging deep survival models and develops differentially private training procedures to provide rigorous privacy protection. The experimental results show that deep survival models leak membership information and our approach effectively reduces membership inference risks. The results also show that differential privacy introduces a limited performance loss, and may improve the model robustness in the presence of noisy data, compared to non-private models.
Collapse
Affiliation(s)
- Liyue Fan
- Dept. of Computer Science, University of North Carolina at Charlotte, Charlotte, NC
| | - Luca Bonomi
- Dept. of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN
| |
Collapse
|
46
|
Zou H, Xiao L, Zeng D, Luo S. Multivariate functional mixed model with MRI data: An application to Alzheimer's disease. Stat Med 2023; 42:1492-1511. [PMID: 36805635 PMCID: PMC10133011 DOI: 10.1002/sim.9683] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Revised: 11/09/2022] [Accepted: 01/26/2023] [Indexed: 02/22/2023]
Abstract
Alzheimer's Disease (AD) is the leading cause of dementia and impairment in various domains. Recent AD studies, (ie, Alzheimer's Disease Neuroimaging Initiative (ADNI) study), collect multimodal data, including longitudinal neurological assessments and magnetic resonance imaging (MRI) data, to better study the disease progression. Adopting early interventions is essential to slow AD progression for subjects with mild cognitive impairment (MCI). It is of particular interest to develop an AD predictive model that leverages multimodal data and provides accurate personalized predictions. In this article, we propose a multivariate functional mixed model with MRI data (MFMM-MRI) that simultaneously models longitudinal neurological assessments, baseline MRI data, and the survival outcome (ie, dementia onset) for subjects with MCI at baseline. Two functional forms (the random-effects model and instantaneous model) linking the longitudinal and survival process are investigated. We use Markov Chain Monte Carlo (MCMC) method based on No-U-Turn Sampling (NUTS) algorithm to obtain posterior samples. We develop a dynamic prediction framework that provides accurate personalized predictions of longitudinal trajectories and survival probability. We apply MFMM-MRI to the ADNI study and identify significant associations among longitudinal outcomes, MRI data, and the risk of dementia onset. The instantaneous model with voxels from the whole brain has the best prediction performance among all candidate models. The simulation study supports the validity of the estimation and dynamic prediction method.
Collapse
Affiliation(s)
- Haotian Zou
- Department of Biostatistics, University of North Carolina, Chapel Hill, North Carolina, United States
| | - Luo Xiao
- Department of Statistics, North Carolina State University, North Carolina, United States
| | - Donglin Zeng
- Department of Biostatistics, University of North Carolina, Chapel Hill, North Carolina, United States
| | - Sheng Luo
- Department of Biostatistics and Bioinformatics, Duke University, North Carolina, United States
| | | |
Collapse
|
47
|
Miller J, Lyden GR, McKinney WT, Snyder JJ, Israni AK. Impacts of removing race from the calculation of the kidney donor profile index. Am J Transplant 2023; 23:636-641. [PMID: 36695678 DOI: 10.1016/j.ajt.2022.12.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Revised: 11/21/2022] [Accepted: 12/10/2022] [Indexed: 01/04/2023]
Abstract
The kidney donor risk index (KDRI), standardized as the kidney donor profile index (KDPI), estimates graft failure risk for organ allocation and includes a coefficient for the Black donor race that could create disparities. This study used the Scientific Registry of Transplant Recipients data to recalculate KDRI coefficients with and without the Black race variable for deceased donor kidney transplants from 1995 to 2005 (n = 69 244). The recalculated coefficients were applied to deceased kidney donors from 2015 to 2021 (n = 72 926) to calculate KDPI. Removing the Black race variable had a negligible impact on the model's predictive ability. When the Black race variable was removed, the proportion of Black donors above KDPI 85%, a category with a higher risk of organ nonuse, declined from 31.09% to 17.75%, closer to the 15.68% above KDPI 85% among non-Black donors. KDPI represents percentiles relative to all other donors, so the number of Black donors moving below KDPI 86% was roughly equal to the number of non-Black donors moving above KDPI 85%. Removing the Black donor indicator from KDRI/KDPI may improve equity without substantial overall impact on the transplantation system, though further improvement may require the use of absolute measures of donor risk KDRI rather than relative measures of risk KDPI.
Collapse
Affiliation(s)
- Jonathan Miller
- Scientific Registry of Transplant Recipients, Hennepin Healthcare Research Institute, Minneapolis, Minnesota, USA.
| | - Grace R Lyden
- Scientific Registry of Transplant Recipients, Hennepin Healthcare Research Institute, Minneapolis, Minnesota, USA
| | - Warren T McKinney
- Scientific Registry of Transplant Recipients, Hennepin Healthcare Research Institute, Minneapolis, Minnesota, USA; Department of Medicine, Hennepin Healthcare, University of Minnesota, Minneapolis, Minnesota, USA
| | - Jon J Snyder
- Scientific Registry of Transplant Recipients, Hennepin Healthcare Research Institute, Minneapolis, Minnesota, USA; Department of Medicine, Hennepin Healthcare, University of Minnesota, Minneapolis, Minnesota, USA; Department of Epidemiology and Community Health, University of Minnesota, Minneapolis, Minnesota, USA
| | - Ajay K Israni
- Scientific Registry of Transplant Recipients, Hennepin Healthcare Research Institute, Minneapolis, Minnesota, USA; Department of Medicine, Hennepin Healthcare, University of Minnesota, Minneapolis, Minnesota, USA; Department of Epidemiology and Community Health, University of Minnesota, Minneapolis, Minnesota, USA
| |
Collapse
|
48
|
Tong R, Zhu Z, Ling J. Comparison of linear and non-linear machine learning models for time-dependent readmission or mortality prediction among hospitalized heart failure patients. Heliyon 2023; 9:e16068. [PMID: 37215773 PMCID: PMC10192765 DOI: 10.1016/j.heliyon.2023.e16068] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Revised: 05/02/2023] [Accepted: 05/04/2023] [Indexed: 05/24/2023] Open
Abstract
Although many models are available to predict prognosis of heart failure patients, most tools combining survival analysis are based on proportional hazard model. Non-linear machine learning algorithms would overcome the limitation of the time-independent hazard ratio assumption and provide more information in readmission or mortality prediction among heart failure patients. The present study collected the clinical information of 1796 hospitalized heart failure patients surviving during hospitalization in a Chinese clinical center from December 2016 to June 2019. A traditional multivariate Cox regression model and three machine learning survival models were developed in derivation cohort. Uno's concordance index and integrated Brier score in validation cohort were calculated to evaluate the discrimination and calibration of different models. Time-dependent AUC and Brier score curves were plotted to assess the performance of models at different time phases.
Collapse
|
49
|
Pelzer KM, Zhang KC, Lazenby KA, Narang N, Churpek MM, Anderson AS, Parker WF. The Accuracy of Initial U.S. Heart Transplant Candidate Rankings. JACC. HEART FAILURE 2023; 11:504-512. [PMID: 37052549 PMCID: PMC10790705 DOI: 10.1016/j.jchf.2023.02.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/11/2022] [Revised: 12/16/2022] [Accepted: 02/01/2023] [Indexed: 04/14/2023]
Abstract
BACKGROUND The U.S. heart allocation system ranks candidates with only 6 treatment-based categorical "statuses" and ignores many objective patient characteristics. OBJECTIVES This study sought to determine the effectiveness of the standard 6-status ranking system and several novel prediction models in identifying the most urgent heart transplant candidates. METHODS The primary outcome was death before receipt of a heart transplant. The accuracy of the 6-status system was evaluated using Harrell's C-index and log-rank tests of Kaplan-Meier estimated survival by status for candidates listed postpolicy (November 2018 to March 2020) in the Scientific Registry of Transplant Recipients data set. The authors then developed Cox proportional hazards models and random survival forest models using prepolicy data (2010-2017). The predictor variables included age, diagnosis, laboratory measurements, hemodynamics, and supportive treatment at the time of listing. The performance of these models was compared with the candidate's 6-status ranking in the postpolicy data. RESULTS Since policy implementation, the 6-status ranking at listing has had moderate ability to rank-order candidates (C-index: 0.67). Statuses 4 and 6 had no significant difference in survival (P = 0.80), and status 5 had lower survival than status 4 (P < 0.001). Novel multivariable prediction models derived with prepolicy data ranked candidates correctly more often than the 6-status rankings (Cox proportional hazards model C-index: 0.76; random survival forest model C-index: 0.74). Objective physiologic measurements, such as glomerular filtration rate, had high variable importance. CONCLUSIONS The treatment-based 6-status heart allocation system has only moderate ability to rank-order candidates by medical urgency. Predictive models that incorporate physiologic measurements can more effectively rank-order heart transplant candidates by urgency.
Collapse
Affiliation(s)
- Kenley M Pelzer
- Department of Medicine, University of Chicago, Chicago, Illinois, USA
| | - Kevin C Zhang
- Department of Medicine, University of Chicago, Chicago, Illinois, USA
| | - Kevin A Lazenby
- Pritzker School of Medicine, University of Chicago, Chicago, Illinois, USA
| | - Nikhil Narang
- Advocate Heart Institute, Advocate Christ Medical Center, Oak Lawn, Illinois, USA; Department of Medicine, University of Illinois-Chicago, Chicago, Illinois, USA
| | - Matthew M Churpek
- Department of Medicine, University of Wisconsin Madison, Madison, Wisconsin, USA
| | - Allen S Anderson
- University of Texas Health Science Center at San Antonio, San Antonio, Texas, USA
| | - William F Parker
- Department of Medicine, University of Chicago, Chicago, Illinois, USA; MacLean Center for Medical Ethics, University of Chicago, Chicago, Illinois, USA.
| |
Collapse
|
50
|
Sonnweber T, Tymoszuk P, Steringer-Mascherbauer R, Sigmund E, Porod-Schneiderbauer S, Kohlbacher L, Theurl I, Lang I, Weiss G, Löffler-Ragg J. The combination of supervised and unsupervised learning based risk stratification and phenotyping in pulmonary arterial hypertension-a long-term retrospective multicenter trial. BMC Pulm Med 2023; 23:143. [PMID: 37098543 PMCID: PMC10131314 DOI: 10.1186/s12890-023-02427-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2022] [Accepted: 04/06/2023] [Indexed: 04/27/2023] Open
Abstract
BACKGROUND Accurate risk stratification in pulmonary arterial hypertension (PAH), a devastating cardiopulmonary disease, is essential to guide successful therapy. Machine learning may improve risk management and harness clinical variability in PAH. METHODS We conducted a long-term retrospective observational study (median follow-up: 67 months) including 183 PAH patients from three Austrian PAH expert centers. Clinical, cardiopulmonary function, laboratory, imaging, and hemodynamic parameters were assessed. Cox proportional hazard Elastic Net and partitioning around medoid clustering were applied to establish a multi-parameter PAH mortality risk signature and investigate PAH phenotypes. RESULTS Seven parameters identified by Elastic Net modeling, namely age, six-minute walking distance, red blood cell distribution width, cardiac index, pulmonary vascular resistance, N-terminal pro-brain natriuretic peptide and right atrial area, constituted a highly predictive mortality risk signature (training cohort: concordance index = 0.82 [95%CI: 0.75 - 0.89], test cohort: 0.77 [0.66 - 0.88]). The Elastic Net signature demonstrated superior prognostic accuracy as compared with five established risk scores. The signature factors defined two clusters of PAH patients with distinct risk profiles. The high-risk/poor prognosis cluster was characterized by advanced age at diagnosis, poor cardiac output, increased red cell distribution width, higher pulmonary vascular resistance, and a poor six-minute walking test performance. CONCLUSION Supervised and unsupervised learning algorithms such as Elastic Net regression and medoid clustering are powerful tools for automated mortality risk prediction and clinical phenotyping in PAH.
Collapse
Affiliation(s)
- Thomas Sonnweber
- Department of Internal Medicine II, Medical University of Innsbruck, Anichstraße 35, 6020, Innsbruck, Austria.
| | - Piotr Tymoszuk
- Data Analytics As a Service Tirol, Daas.Tirol, Innsbruck, Austria
| | | | | | | | - Lisa Kohlbacher
- Department of Cardiology, Medical University of Vienna, Vienna, Austria
| | - Igor Theurl
- Department of Internal Medicine II, Medical University of Innsbruck, Anichstraße 35, 6020, Innsbruck, Austria
| | - Irene Lang
- Department of Cardiology, Medical University of Vienna, Vienna, Austria
| | - Günter Weiss
- Department of Internal Medicine II, Medical University of Innsbruck, Anichstraße 35, 6020, Innsbruck, Austria
| | - Judith Löffler-Ragg
- Department of Internal Medicine II, Medical University of Innsbruck, Anichstraße 35, 6020, Innsbruck, Austria
| |
Collapse
|