1
|
Xu QT, Qiang JK, Huang ZY, Jiang WJ, Cui XM, Hu RH, Wang T, Yi XL, Li JY, Yu Z, Zhang S, Du T, Liu J, Jiang XH. Integration of machine learning for developing a prognostic signature related to programmed cell death in colorectal cancer. ENVIRONMENTAL TOXICOLOGY 2024; 39:2908-2926. [PMID: 38299230 DOI: 10.1002/tox.24157] [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: 12/08/2023] [Revised: 01/04/2024] [Accepted: 01/18/2024] [Indexed: 02/02/2024]
Abstract
BACKGROUND Colorectal cancer (CRC) presents a significant global health burden, characterized by a heterogeneous molecular landscape and various genetic and epigenetic alterations. Programmed cell death (PCD) plays a critical role in CRC, offering potential targets for therapy by regulating cell elimination processes that can suppress tumor growth or trigger cancer cell resistance. Understanding the complex interplay between PCD mechanisms and CRC pathogenesis is crucial. This study aims to construct a PCD-related prognostic signature in CRC using machine learning integration, enhancing the precision of CRC prognosis prediction. METHOD We retrieved expression data and clinical information from the Cancer Genome Atlas and Gene Expression Omnibus (GEO) datasets. Fifteen forms of PCD were identified, and corresponding gene sets were compiled. Machine learning algorithms, including Lasso, Ridge, Enet, StepCox, survivalSVM, CoxBoost, SuperPC, plsRcox, random survival forest (RSF), and gradient boosting machine, were integrated for model construction. The models were validated using six GEO datasets, and the programmed cell death score (PCDS) was established. Further, the model's effectiveness was compared with 109 transcriptome-based CRC prognostic models. RESULT Our integrated model successfully identified differentially expressed PCD-related genes and stratified CRC samples into four subtypes with distinct prognostic implications. The optimal combination of machine learning models, RSF + Ridge, showed superior performance compared with traditional methods. The PCDS effectively stratified patients into high-risk and low-risk groups, with significant survival differences. Further analysis revealed the prognostic relevance of immune cell types and pathways associated with CRC subtypes. The model also identified hub genes and drug sensitivities relevant to CRC prognosis. CONCLUSION The current study highlights the potential of integrating machine learning models to enhance the prediction of CRC prognosis. The developed prognostic signature, which is related to PCD, holds promise for personalized and effective therapeutic interventions in CRC.
Collapse
Affiliation(s)
- Qi-Tong Xu
- Department of Gastrointestinal Surgery, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Jian-Kun Qiang
- Key Laboratory of Arrhythmias of the Ministry of Education of China, Tongji University School of Medicine, Shanghai, China
| | - Zhi-Ye Huang
- Department of Gastrointestinal Surgery, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Wan-Ju Jiang
- Department of Gastrointestinal Surgery, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Xi-Mao Cui
- Department of Gastrointestinal Surgery, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Ren-Hao Hu
- Department of Gastrointestinal Surgery, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Tao Wang
- Key Laboratory of Arrhythmias of the Ministry of Education of China, Tongji University School of Medicine, Shanghai, China
| | - Xiang-Lan Yi
- Key Laboratory of Arrhythmias of the Ministry of Education of China, Tongji University School of Medicine, Shanghai, China
| | - Jia-Yuan Li
- Key Laboratory of Arrhythmias of the Ministry of Education of China, Tongji University School of Medicine, Shanghai, China
| | - Zuoren Yu
- Key Laboratory of Arrhythmias of the Ministry of Education of China, Tongji University School of Medicine, Shanghai, China
| | - Shun Zhang
- Department of Gastrointestinal Surgery, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Tao Du
- Department of Gastrointestinal Surgery, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Jinhui Liu
- Department of Gynecology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Xiao-Hua Jiang
- Department of Gastrointestinal Surgery, Shanghai East Hospital, School of Medicine, Tongji University, Shanghai, China
| |
Collapse
|
2
|
Sheehy J, Rutledge H, Acharya UR, Loh HW, Gururajan R, Tao X, Zhou X, Li Y, Gurney T, Kondalsamy-Chennakesavan S. Gynecological cancer prognosis using machine learning techniques: A systematic review of last three decades (1990–2022). Artif Intell Med 2023; 139:102536. [PMID: 37100507 DOI: 10.1016/j.artmed.2023.102536] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2021] [Revised: 03/19/2023] [Accepted: 03/23/2023] [Indexed: 03/30/2023]
Abstract
OBJECTIVE Many Computer Aided Prognostic (CAP) systems based on machine learning techniques have been proposed in the field of oncology. The objective of this systematic review was to assess and critically appraise the methodologies and approaches used in predicting the prognosis of gynecological cancers using CAPs. METHODS Electronic databases were used to systematically search for studies utilizing machine learning methods in gynecological cancers. Study risk of bias (ROB) and applicability were assessed using the PROBAST tool. 139 studies met the inclusion criteria, of which 71 predicted outcomes for ovarian cancer patients, 41 predicted outcomes for cervical cancer patients, 28 predicted outcomes for uterine cancer patients, and 2 predicted outcomes for gynecological malignancies broadly. RESULTS Random forest (22.30 %) and support vector machine (21.58 %) classifiers were used most commonly. Use of clinicopathological, genomic and radiomic data as predictors was observed in 48.20 %, 51.08 % and 17.27 % of studies, respectively, with some studies using multiple modalities. 21.58 % of studies were externally validated. Twenty-three individual studies compared ML and non-ML methods. Study quality was highly variable and methodologies, statistical reporting and outcome measures were inconsistent, preventing generalized commentary or meta-analysis of performance outcomes. CONCLUSION There is significant variability in model development when prognosticating gynecological malignancies with respect to variable selection, machine learning (ML) methods and endpoint selection. This heterogeneity prevents meta-analysis and conclusions regarding the superiority of ML methods. Furthermore, PROBAST-mediated ROB and applicability analysis demonstrates concern for the translatability of existing models. This review identifies ways that this can be improved upon in future works to develop robust, clinically translatable models within this promising field.
Collapse
|
3
|
A combination of ridge and Liu regressions for extreme learning machine. Soft comput 2023; 27:2493-2508. [PMID: 36573103 PMCID: PMC9774081 DOI: 10.1007/s00500-022-07745-x] [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] [Accepted: 12/09/2022] [Indexed: 12/24/2022]
Abstract
Extreme learning machine (ELM) as a type of feedforward neural network has been widely used to obtain beneficial insights from various disciplines and real-world applications. Despite the advantages like speed and highly adaptability, instability drawbacks arise in case of multicollinearity, and to overcome this, additional improvements were needed. Regularization is one of the best choices to overcome these drawbacks. Although ridge and Liu regressions have been considered and seemed effective regularization methods on ELM algorithm, each one has own characteristic features such as the form of tuning parameter, the level of shrinkage or the norm of coefficients. Instead of focusing on one of these regularization methods, we propose a combination of ridge and Liu regressions in a unified form for the context of ELM as a remedy to aforementioned drawbacks. To investigate the performance of the proposed algorithm, comprehensive comparisons have been carried out by using various real-world data sets. Based on the results, it is obtained that the proposed algorithm is more effective than the ELM and its variants based on ridge and Liu regressions, RR-ELM and Liu-ELM, in terms of the capability of generalization. Generalization performance of proposed algorithm on ELM is remarkable when compared to RR-ELM and Liu-ELM, and the generalization performance of the proposed algorithm on ELM increases as the number of nodes increases. The proposed algorithm outperforms ELM in all data sets and all node numbers in that it has a smaller norm and standard deviation of the norm. Additionally, it should be noted that the proposed algorithm can be applied for both regression and classification problems.
Collapse
|
4
|
Deep survival forests with feature screening. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104195] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
5
|
Bachega FS, Suartz CV, Almeida MQ, Brondani VB, Charchar HLS, Lacombe AMF, Martins-Filho SN, Soares IC, Zerbini MCN, Dénes FT, Mendonca B, Lopes RI, Latronico AC, Fragoso MCBV. Retrospective Analysis of Prognostic Factors in Pediatric Patients with Adrenocortical Tumor from Unique Tertiary Center with Long-Term Follow-Up. J Clin Med 2022; 11:jcm11226641. [PMID: 36431124 PMCID: PMC9692695 DOI: 10.3390/jcm11226641] [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: 09/28/2022] [Revised: 11/06/2022] [Accepted: 11/07/2022] [Indexed: 11/11/2022] Open
Abstract
Pediatric adrenocortical tumors (PACTs) represent rare causes of malignancies. However, the south/southeast regions of Brazil are known to have a high incidence of PACTs because of the founder effect associated with a germline pathogenic variant of tumor suppressor gene TP53. We aimed to retrospectively analyze the types of variables among hormone production, radiological imaging, tumor staging, histological and genetic features that were associated with the occurrence of malignancy in 95 patients (71% females) with PACTs from a unique center. The worst prognosis was associated with those aged > 3 years (p < 0.05), high serum levels of 11-desoxicortisol (p < 0.001), tumor weight ≥ 200 g (p < 0.001), tumor size ≥ 5 cm (p < 0.05), Weiss score ≥ 5 (p < 0.05), Wieneke index ≥ 3 (p < 0.001) and Ki67 ≥ 15% (p < 0.05). Furthermore, patients with MacFarlane stage IV had an overall survival rate almost two times shorter than patients with other stages (p < 0.001). Additionally, the subtractions of BUB1B-PINK1 (<6.95) expression (p < 0.05) and IGF-IR overexpression (p = 0.0001) were associated with malignant behavior. These results helped identify patients who are likely to have an aggressive course; further multicenter prospective studies are required to confirm our results. In conclusion, PACTs with these patterns of prognostic factors could be treated using an adjuvant approach that may improve the overall survival in such patients.
Collapse
Affiliation(s)
- Fernanda S. Bachega
- Unidade de Suprarrenal, Laboratório de Hormônios e Genética Molecular LIM/42, Disciplina de Endocrinologia e Metabologia, Hospital das Clínicas, Faculdade de Medicina da Universidade de São Paulo, São Paulo 05466-040, SP, Brazil
| | - Caio V. Suartz
- Divisão de Urologia, Departamento de Cirurgia da Faculdade de Medicina da Universidade de São Paulo, São Paulo 1964-2007, SP, Brazil
| | - Madson Q. Almeida
- Unidade de Suprarrenal, Laboratório de Hormônios e Genética Molecular LIM/42, Disciplina de Endocrinologia e Metabologia, Hospital das Clínicas, Faculdade de Medicina da Universidade de São Paulo, São Paulo 05466-040, SP, Brazil
| | - Vania B. Brondani
- Unidade de Suprarrenal, Laboratório de Hormônios e Genética Molecular LIM/42, Disciplina de Endocrinologia e Metabologia, Hospital das Clínicas, Faculdade de Medicina da Universidade de São Paulo, São Paulo 05466-040, SP, Brazil
| | - Helaine L. S. Charchar
- Unidade de Suprarrenal, Laboratório de Hormônios e Genética Molecular LIM/42, Disciplina de Endocrinologia e Metabologia, Hospital das Clínicas, Faculdade de Medicina da Universidade de São Paulo, São Paulo 05466-040, SP, Brazil
| | - Amanda M. F. Lacombe
- Unidade de Suprarrenal, Laboratório de Hormônios e Genética Molecular LIM/42, Disciplina de Endocrinologia e Metabologia, Hospital das Clínicas, Faculdade de Medicina da Universidade de São Paulo, São Paulo 05466-040, SP, Brazil
| | - Sebastião N. Martins-Filho
- Departamento de Patologia, Faculdade de Medicina da Universidade de São Paulo, São Paulo 01246-903, SP, Brazil
| | - Iberê C. Soares
- Departamento de Patologia, Faculdade de Medicina da Universidade de São Paulo, São Paulo 01246-903, SP, Brazil
| | - Maria Claudia N. Zerbini
- Departamento de Patologia, Faculdade de Medicina da Universidade de São Paulo, São Paulo 01246-903, SP, Brazil
| | - Francisco T. Dénes
- Divisão de Urologia, Departamento de Cirurgia da Faculdade de Medicina da Universidade de São Paulo, São Paulo 1964-2007, SP, Brazil
| | - Berenice Mendonca
- Unidade de Suprarrenal, Laboratório de Hormônios e Genética Molecular LIM/42, Disciplina de Endocrinologia e Metabologia, Hospital das Clínicas, Faculdade de Medicina da Universidade de São Paulo, São Paulo 05466-040, SP, Brazil
| | - Roberto I. Lopes
- Divisão de Urologia, Departamento de Cirurgia da Faculdade de Medicina da Universidade de São Paulo, São Paulo 1964-2007, SP, Brazil
| | - Ana Claudia Latronico
- Unidade de Suprarrenal, Laboratório de Hormônios e Genética Molecular LIM/42, Disciplina de Endocrinologia e Metabologia, Hospital das Clínicas, Faculdade de Medicina da Universidade de São Paulo, São Paulo 05466-040, SP, Brazil
| | - Maria Candida B. V. Fragoso
- Unidade de Suprarrenal, Laboratório de Hormônios e Genética Molecular LIM/42, Disciplina de Endocrinologia e Metabologia, Hospital das Clínicas, Faculdade de Medicina da Universidade de São Paulo, São Paulo 05466-040, SP, Brazil
- Correspondence:
| |
Collapse
|
6
|
Lin C, Qiao N, Zhang W, Li Y, Ma S. Default risk prediction and feature extraction using a penalized deep neural network. STATISTICS AND COMPUTING 2022; 32:76. [PMID: 36124203 PMCID: PMC9476445 DOI: 10.1007/s11222-022-10140-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/28/2022] [Accepted: 08/26/2022] [Indexed: 06/15/2023]
Abstract
Online peer-to-peer lending platforms provide loans directly from lenders to borrowers without passing through traditional financial institutions. For lenders on these platforms to avoid loss, it is crucial that they accurately assess default risk so that they can make appropriate decisions. In this study, we develop a penalized deep learning model to predict default risk based on survival data. As opposed to simply predicting whether default will occur, we focus on predicting the probability of default over time. Moreover, by adding an additional one-to-one layer in the neural network, we achieve feature selection and estimation simultaneously by incorporating an L 1 -penalty into the objective function. The minibatch gradient descent algorithm makes it possible to handle massive data. An analysis of a real-world loan data and simulations demonstrate the model's competitive practical performance, which suggests favorable potential applications in peer-to-peer lending platforms.
Collapse
Affiliation(s)
- Cunjie Lin
- Center for Applied Statistics, Renmin University of China, Beijing, 100872 China
- School of Statistics, Renmin University of China, Beijing, 100872 China
| | - Nan Qiao
- School of Statistics, Renmin University of China, Beijing, 100872 China
| | - Wenli Zhang
- School of Statistics, Renmin University of China, Beijing, 100872 China
| | - Yang Li
- Center for Applied Statistics, Renmin University of China, Beijing, 100872 China
- School of Statistics, Renmin University of China, Beijing, 100872 China
- Statistical Consulting Center, Renmin University of China, Beijing, 100872 China
| | - Shuangge Ma
- School of Statistics, Renmin University of China, Beijing, 100872 China
- Department of Biostatistics, Yale University, New Haven, CT 06511 USA
| |
Collapse
|
7
|
Deep survival forests for extremely high censored data. APPL INTELL 2022. [DOI: 10.1007/s10489-022-03846-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
|
8
|
Smith H, Sweeting M, Morris T, Crowther MJ. A scoping methodological review of simulation studies comparing statistical and machine learning approaches to risk prediction for time-to-event data. Diagn Progn Res 2022; 6:10. [PMID: 35650647 PMCID: PMC9161606 DOI: 10.1186/s41512-022-00124-y] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/01/2021] [Accepted: 03/01/2022] [Indexed: 12/24/2022] Open
Abstract
BACKGROUND There is substantial interest in the adaptation and application of so-called machine learning approaches to prognostic modelling of censored time-to-event data. These methods must be compared and evaluated against existing methods in a variety of scenarios to determine their predictive performance. A scoping review of how machine learning methods have been compared to traditional survival models is important to identify the comparisons that have been made and issues where they are lacking, biased towards one approach or misleading. METHODS We conducted a scoping review of research articles published between 1 January 2000 and 2 December 2020 using PubMed. Eligible articles were those that used simulation studies to compare statistical and machine learning methods for risk prediction with a time-to-event outcome in a medical/healthcare setting. We focus on data-generating mechanisms (DGMs), the methods that have been compared, the estimands of the simulation studies, and the performance measures used to evaluate them. RESULTS A total of ten articles were identified as eligible for the review. Six of the articles evaluated a method that was developed by the authors, four of which were machine learning methods, and the results almost always stated that this developed method's performance was equivalent to or better than the other methods compared. Comparisons were often biased towards the novel approach, with the majority only comparing against a basic Cox proportional hazards model, and in scenarios where it is clear it would not perform well. In many of the articles reviewed, key information was unclear, such as the number of simulation repetitions and how performance measures were calculated. CONCLUSION It is vital that method comparisons are unbiased and comprehensive, and this should be the goal even if realising it is difficult. Fully assessing how newly developed methods perform and how they compare to a variety of traditional statistical methods for prognostic modelling is imperative as these methods are already being applied in clinical contexts. Evaluations of the performance and usefulness of recently developed methods for risk prediction should be continued and reporting standards improved as these methods become increasingly popular.
Collapse
Affiliation(s)
- Hayley Smith
- grid.9918.90000 0004 1936 8411Department of Health Sciences, University of Leicester, Leicester, LE1 7RH UK
| | - Michael Sweeting
- grid.9918.90000 0004 1936 8411Department of Health Sciences, University of Leicester, Leicester, LE1 7RH UK
- grid.417815.e0000 0004 5929 4381Statistical Innovation, Oncology Biometrics, Oncology R&D, AstraZeneca, Cambridge, UK
| | - Tim Morris
- grid.415052.70000 0004 0606 323XMRC Clinical Trials Unit at UCL, 90 High Holborn, London, WC1V 6LJ UK
| | - Michael J. Crowther
- grid.4714.60000 0004 1937 0626Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden
| |
Collapse
|
9
|
He Y, Ye X, Huang JZ, Fournier-Viger P. Bayesian Attribute Bagging-Based Extreme Learning Machine for High-Dimensional Classification and Regression. ACM T INTEL SYST TEC 2022. [DOI: 10.1145/3495164] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
Abstract
This article presents a Bayesian attribute
bagging-based extreme learning machine (BAB-ELM)
to handle high-dimensional classification and regression problems. First, the
decision-making degree (DMD)
of a condition attribute is calculated based on the Bayesian decision theory, i.e., the conditional probability of the condition attribute given the decision attribute. Second, the condition attribute with the highest DMD is put into the
condition attribute group (CAG)
corresponding to the specific decision attribute. Third, the
bagging attribute groups (BAGs)
are used to train an ensemble learning model of
extreme learning machines (ELMs).
Each base ELM is trained on a BAG which is composed of condition attributes that are randomly selected from the CAGs. Fourth, the information amount ratios of bagging condition attributes to all condition attributes is used as the weights to fuse the predictions of base ELMs in BAB-ELM. Exhaustive experiments have been conducted to compare the feasibility and effectiveness of BAB-ELM with seven other ELM models, i.e., ELM, ensemble-based ELM (EN-ELM), voting-based ELM (V-ELM), ensemble ELM (E-ELM), ensemble ELM based on multi-activation functions (MAF-EELM), bagging ELM, and simple ensemble ELM. Experimental results show that BAB-ELM is convergent with the increase of base ELMs and also can yield higher classification accuracy and lower regression error for high-dimensional classification and regression problems.
Collapse
Affiliation(s)
- Yulin He
- College of Computer Science & Software Engineering, Shenzhen University, Shenzhen, Guangdong, China
| | - Xuan Ye
- College of Computer Science & Software Engineering, Shenzhen University, Shenzhen, Guangdong, China
| | - Joshua Zhexue Huang
- College of Computer Science & Software Engineering, Shenzhen University, Shenzhen, Guangdong, China
| | - Philippe Fournier-Viger
- College of Computer Science & Software Engineering, Shenzhen University, Shenzhen, Guangdong, China
| |
Collapse
|
10
|
Zhuang XD, Tian T, Liao LZ, Dong YH, Zhou HJ, Zhang SZ, Chen WY, Du ZM, Wang XQ, Liao XX. Deep Phenotyping and Prediction of Long-Term Cardiovascular Disease: Optimized by Machine Learning. Can J Cardiol 2022; 38:774-782. [DOI: 10.1016/j.cjca.2022.02.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2020] [Revised: 01/16/2022] [Accepted: 02/03/2022] [Indexed: 11/29/2022] Open
|
11
|
A Simulation Study to Compare the Predictive Performance of Survival Neural Networks with Cox Models for Clinical Trial Data. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2021; 2021:2160322. [PMID: 34880930 PMCID: PMC8646180 DOI: 10.1155/2021/2160322] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/17/2021] [Accepted: 11/10/2021] [Indexed: 12/23/2022]
Abstract
Background Studies focusing on prediction models are widespread in medicine. There is a trend in applying machine learning (ML) by medical researchers and clinicians. Over the years, multiple ML algorithms have been adapted to censored data. However, the choice of methodology should be motivated by the real-life data and their complexity. Here, the predictive performance of ML techniques is compared with statistical models in a simple clinical setting (small/moderate sample size and small number of predictors) with Monte-Carlo simulations. Methods Synthetic data (250 or 1000 patients) were generated that closely resembled 5 prognostic factors preselected based on a European Osteosarcoma Intergroup study (MRC BO06/EORTC 80931). Comparison was performed between 2 partial logistic artificial neural networks (PLANNs) and Cox models for 20, 40, 61, and 80% censoring. Survival times were generated from a log-normal distribution. Models were contrasted in terms of the C-index, Brier score at 0-5 years, integrated Brier score (IBS) at 5 years, and miscalibration at 2 and 5 years (usually neglected). The endpoint of interest was overall survival. Results PLANNs original/extended were tuned based on the IBS at 5 years and the C-index, achieving a slightly better performance with the IBS. Comparison with Cox models showed that PLANNs can reach similar predictive performance on simulated data for most scenarios with respect to the C-index, Brier score, or IBS. However, Cox models were frequently less miscalibrated. Performance was robust in scenario data where censored patients were removed before 2 years or curtailing at 5 years was performed (on training data). Conclusion Survival neural networks reached a comparable predictive performance with Cox models but were generally less well calibrated. All in all, researchers should be aware of burdensome aspects of ML techniques such as data preprocessing, tuning of hyperparameters, and computational intensity that render them disadvantageous against conventional regression models in a simple clinical setting.
Collapse
|
12
|
Yang H, Tian J, Meng B, Wang K, Zheng C, Liu Y, Yan J, Han Q, Zhang Y. Application of Extreme Learning Machine in the Survival Analysis of Chronic Heart Failure Patients With High Percentage of Censored Survival Time. Front Cardiovasc Med 2021; 8:726516. [PMID: 34778396 PMCID: PMC8586069 DOI: 10.3389/fcvm.2021.726516] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2021] [Accepted: 10/08/2021] [Indexed: 12/05/2022] Open
Abstract
Objective: To explore the application of the Cox model based on extreme learning machine in the survival analysis of patients with chronic heart failure. Methods: The medical records of 5,279 inpatients diagnosed with chronic heart failure in two grade 3 and first-class hospitals in Taiyuan from 2014 to 2019 were collected; with death as the outcome and after the feature selection, the Lasso Cox, random survival forest (RSF), and the Cox model based on extreme learning machine (ELM Cox) were constructed for survival analysis and prediction; the prediction performance of the three models was explored based on simulated data with three censoring ratios of 25, 50, and 75%. Results: Simulation results showed that the prediction performance of the three models decreased with increasing censoring proportion, and the ELM Cox model performed best overall; the ELM Cox model constructed with 21 highly influential survival predictors screened from actual chronic heart failure data showed the best performance with C-index and Integrated Brier Score (IBS) of 0.775(0.755, 0.802) and 0.166(0.150, 0.182), respectively. Conclusion: The ELM Cox model showed good discrimination performance in the survival analysis of patients with chronic heart failure; it performs consistently for data with a high proportion of censored survival time; therefore, the model could help physicians identify patients at high risk of poor prognosis and target therapeutic measures to patients as early as possible.
Collapse
Affiliation(s)
- Hong Yang
- Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, China.,Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan, China
| | - Jing Tian
- Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan, China.,Department of Cardiology, The First Hospital of Shanxi Medical University, Taiyuan, China
| | - Bingxia Meng
- Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, China.,Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan, China
| | - Ke Wang
- Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, China.,Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan, China
| | - Chu Zheng
- Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, China.,Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan, China
| | - Yanling Liu
- Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, China.,Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan, China
| | - Jingjing Yan
- Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, China.,Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan, China
| | - Qinghua Han
- Department of Cardiology, The First Hospital of Shanxi Medical University, Taiyuan, China
| | - Yanbo Zhang
- Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, China.,Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan, China
| |
Collapse
|
13
|
Zhang Z, Shen Z, Wang H, Ng SK. A fast adaptive Lasso for the cox regression via safe screening rules. J STAT COMPUT SIM 2021. [DOI: 10.1080/00949655.2021.1914043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
Affiliation(s)
- Zhuan Zhang
- School of Mathematics and Statistics, Central South University, Changsha, People's Republic of China
| | - Zhenyuan Shen
- School of Mathematics and Statistics, Central South University, Changsha, People's Republic of China
| | - Hong Wang
- School of Mathematics and Statistics, Central South University, Changsha, People's Republic of China
| | - Shu Kay Ng
- School of Medicine, Menzies Health Institute Queensland, Griffith University, Nathan, Australia
| |
Collapse
|
14
|
Wilson CM, Li K, Sun Q, Kuan PF, Wang X. Fenchel duality of Cox partial likelihood with an application in survival kernel learning. Artif Intell Med 2021; 116:102077. [PMID: 34020756 PMCID: PMC8159024 DOI: 10.1016/j.artmed.2021.102077] [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: 05/19/2020] [Revised: 04/14/2021] [Accepted: 04/19/2021] [Indexed: 11/30/2022]
Abstract
The Cox proportional hazard model is one of the most widely used methods in modeling time-to-event data in the health sciences. Due to the simplicity of the Cox partial likelihood function, many machine learning algorithms use it for survival data. However, due to the nature of censored data, the optimization problem becomes intractable when more complicated regularization is employed, which is necessary when dealing with high dimensional omic data. In this paper, we show that a convex conjugate function of the Cox loss function based on Fenchel duality exists, and provide an alternative framework to optimization based on the primal form. Furthermore, the dual form suggests an efficient algorithm for solving the kernel learning problem with censored survival outcomes. We illustrate performance and properties of the derived duality form of Cox partial likelihood loss in multiple kernel learning problems with simulated and the Skin Cutaneous Melanoma TCGA datasets.
Collapse
Affiliation(s)
- Christopher M Wilson
- Department of Biostatistics and Bioinformatics, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL 33612, USA
| | - Kaiqiao Li
- Department of Applied Math & Statistics, Stony Brook University, Stony Brook, NY 11794, USA
| | - Qiang Sun
- Department of Statistical Sciences, University of Toronto, Ontario M5S 3G3, Canada
| | - Pei Fen Kuan
- Department of Applied Math & Statistics, Stony Brook University, Stony Brook, NY 11794, USA
| | - Xuefeng Wang
- Department of Biostatistics and Bioinformatics, H. Lee Moffitt Cancer Center & Research Institute, Tampa, FL 33612, USA.
| |
Collapse
|
15
|
Abstract
With the development of high-throughput technologies, more and more high-dimensional or ultra-high-dimensional genomic data are being generated. Therefore, effectively analyzing such data has become a significant challenge. Machine learning (ML) algorithms have been widely applied for modeling nonlinear and complicated interactions in a variety of practical fields such as high-dimensional survival data. Recently, multilayer deep neural network (DNN) models have made remarkable achievements. Thus, a Cox-based DNN prediction survival model (DNNSurv model), which was built with Keras and TensorFlow, was developed. However, its results were only evaluated on the survival datasets with high-dimensional or large sample sizes. In this paper, we evaluated the prediction performance of the DNNSurv model using ultra-high-dimensional and high-dimensional survival datasets and compared it with three popular ML survival prediction models (i.e., random survival forest and the Cox-based LASSO and Ridge models). For this purpose, we also present the optimal setting of several hyperparameters, including the selection of a tuning parameter. The proposed method demonstrated via data analysis that the DNNSurv model performed well overall as compared with the ML models, in terms of the three main evaluation measures (i.e., concordance index, time-dependent Brier score, and the time-dependent AUC) for survival prediction performance.
Collapse
|
16
|
Herrin J, Abraham NS, Yao X, Noseworthy PA, Inselman J, Shah ND, Ngufor C. Comparative Effectiveness of Machine Learning Approaches for Predicting Gastrointestinal Bleeds in Patients Receiving Antithrombotic Treatment. JAMA Netw Open 2021; 4:e2110703. [PMID: 34019087 PMCID: PMC8140376 DOI: 10.1001/jamanetworkopen.2021.10703] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/14/2022] Open
Abstract
IMPORTANCE Anticipating the risk of gastrointestinal bleeding (GIB) when initiating antithrombotic treatment (oral antiplatelets or anticoagulants) is limited by existing risk prediction models. Machine learning algorithms may result in superior predictive models to aid in clinical decision-making. OBJECTIVE To compare the performance of 3 machine learning approaches with the commonly used HAS-BLED (hypertension, abnormal kidney and liver function, stroke, bleeding, labile international normalized ratio, older age, and drug or alcohol use) risk score in predicting antithrombotic-related GIB. DESIGN, SETTING, AND PARTICIPANTS This retrospective cross-sectional study used data from the OptumLabs Data Warehouse, which contains medical and pharmacy claims on privately insured patients and Medicare Advantage enrollees in the US. The study cohort included patients 18 years or older with a history of atrial fibrillation, ischemic heart disease, or venous thromboembolism who were prescribed oral anticoagulant and/or thienopyridine antiplatelet agents between January 1, 2016, and December 31, 2019. EXPOSURES A cohort of patients prescribed oral anticoagulant and thienopyridine antiplatelet agents was divided into development and validation cohorts based on date of index prescription. The development cohort was used to train 3 machine learning models to predict GIB at 6 and 12 months: regularized Cox proportional hazards regression (RegCox), random survival forests (RSF), and extreme gradient boosting (XGBoost). MAIN OUTCOMES AND MEASURES The performance of the models for predicting GIB in the validation cohort, evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, and prediction density plots. Relative importance scores were used to identify the variables that were most influential in the top-performing machine learning model. RESULTS In the entire study cohort of 306 463 patients, 166 177 (54.2%) were male, 193 648 (63.2%) were White, the mean (SD) age was 69.0 (12.6) years, and 12 322 (4.0%) had experienced a GIB. In the validation data set, the HAS-BLED model had an AUC of 0.60 for predicting GIB at 6 months and 0.59 at 12 months. The RegCox model performed the best in the validation set, with an AUC of 0.67 at 6 months and 0.66 at 12 months. XGBoost was similar, with AUCs of 0.67 at 6 months and 0.66 at 12 months, whereas for RSF, AUCs were 0.62 at 6 months and 0.60 at 12 months. The variables with the highest importance scores in the RegCox model were prior GI bleed (importance score, 0.72); atrial fibrillation, ischemic heart disease, and venous thromboembolism combined (importance score, 0.38); and use of gastroprotective agents (importance score, 0.32). CONCLUSIONS AND RELEVANCE In this cross-sectional study, the machine learning models examined showed similar performance in identifying patients at high risk for GIB after being prescribed antithrombotic agents. Two models (RegCox and XGBoost) performed modestly better than the HAS-BLED score. A prospective evaluation of the RegCox model compared with HAS-BLED may provide a better understanding of the clinical impact of improved performance.
Collapse
Affiliation(s)
- Jeph Herrin
- Division of Cardiology, Yale School of Medicine, New Haven, Connecticut
| | - Neena S. Abraham
- Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Scottsdale, Arizona
- Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, Minnesota
- Division of Health Care Delivery Research, Mayo Clinic, Rochester, Minnesota
| | - Xiaoxi Yao
- Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, Minnesota
- Division of Health Care Delivery Research, Mayo Clinic, Rochester, Minnesota
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| | - Peter A. Noseworthy
- Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, Minnesota
- Division of Health Care Delivery Research, Mayo Clinic, Rochester, Minnesota
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| | - Jonathan Inselman
- Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, Minnesota
- Division of Health Care Delivery Research, Mayo Clinic, Rochester, Minnesota
| | - Nilay D. Shah
- Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, Minnesota
- Division of Health Care Delivery Research, Mayo Clinic, Rochester, Minnesota
- OptumLabs, Cambridge, Massachusetts
| | - Che Ngufor
- Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, Minnesota
- Division of Health Care Delivery Research, Mayo Clinic, Rochester, Minnesota
- Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, Minnesota
| |
Collapse
|
17
|
Yıldırım H, Revan Özkale M. LL-ELM: A regularized extreme learning machine based on $$L_{1}$$-norm and Liu estimator. Neural Comput Appl 2021. [DOI: 10.1007/s00521-021-05806-0] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/01/2022]
|
18
|
A joint optimization framework to semi-supervised RVFL and ELM networks for efficient data classification. Appl Soft Comput 2020. [DOI: 10.1016/j.asoc.2020.106756] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
|
19
|
Dhillon A, Singh A. eBreCaP: extreme learning-based model for breast cancer survival prediction. IET Syst Biol 2020; 14:160-169. [PMID: 32406380 PMCID: PMC8687246 DOI: 10.1049/iet-syb.2019.0087] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2019] [Revised: 03/19/2020] [Accepted: 03/26/2020] [Indexed: 01/17/2023] Open
Abstract
Breast cancer is the second leading cause of death in the world. Breast cancer research is focused towards its early prediction, diagnosis, and prognosis. Breast cancer can be predicted on omics profiles, clinical tests, and pathological images. The omics profiles comprise of genomic, proteomic, and transcriptomic profiles that are available as high-dimensional datasets. Survival prediction is carried out on omics data to predict early the onset of disease, relapse, reoccurrence of diseases, and biomarker identification. The early prediction of breast cancer is desired for the effective treatment of patients as delay can aggravate the staging of cancer. In this study, extreme learning machine (ELM) based model for breast cancer survival prediction named eBreCaP is proposed. It integrates the genomic (gene expression, copy number alteration, DNA methylation, protein expression) and pathological image datasets; and trains them using an ensemble of ELM with the six best-chosen models suitable to be applied on integrated data. eBreCaP has been evaluated on nine performance parameters, namely sensitivity, specificity, precision, accuracy, Matthews correlation coefficient, area under curve, area under precision-recall, hazard ratio, and concordance Index. eBreCaP has achieved an accuracy of 85% for early breast cancer survival prediction using the ensemble of ELM with gradient boosting.
Collapse
Affiliation(s)
- Arwinder Dhillon
- Computer Science and Engineering Department, Thapar Institute of Engineering and Technology, Patiala, Punjab 147001, India.
| | - Ashima Singh
- Computer Science and Engineering Department, Thapar Institute of Engineering and Technology, Patiala, Punjab 147001, India
| |
Collapse
|
20
|
Zhao N, Xu Q, Tang ML, Wang H. Variable Screening for Near Infrared (NIR) Spectroscopy Data Based on Ridge Partial Least Squares Regression. Comb Chem High Throughput Screen 2020; 23:740-756. [PMID: 32342803 DOI: 10.2174/1386207323666200428114823] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2019] [Revised: 01/17/2020] [Accepted: 02/29/2020] [Indexed: 11/22/2022]
Abstract
AIM AND OBJECTIVE Near Infrared (NIR) spectroscopy data are featured by few dozen to many thousands of samples and highly correlated variables. Quantitative analysis of such data usually requires a combination of analytical methods with variable selection or screening methods. Commonly-used variable screening methods fail to recover the true model when (i) some of the variables are highly correlated, and (ii) the sample size is less than the number of relevant variables. In these cases, Partial Least Squares (PLS) regression based approaches can be useful alternatives. MATERIALS AND METHODS In this research, a fast variable screening strategy, namely the preconditioned screening for ridge partial least squares regression (PSRPLS), is proposed for modelling NIR spectroscopy data with high-dimensional and highly correlated covariates. Under rather mild assumptions, we prove that using Puffer transformation, the proposed approach successfully transforms the problem of variable screening with highly correlated predictor variables to that of weakly correlated covariates with less extra computational effort. RESULTS We show that our proposed method leads to theoretically consistent model selection results. Four simulation studies and two real examples are then analyzed to illustrate the effectiveness of the proposed approach. CONCLUSION By introducing Puffer transformation, high correlation problem can be mitigated using the PSRPLS procedure we construct. By employing RPLS regression to our approach, it can be made more simple and computational efficient to cope with the situation where model size is larger than the sample size while maintaining a high precision prediction.
Collapse
Affiliation(s)
- Naifei Zhao
- School of Mathematics and Statistics, Changsha University of Science & Technology, Changsha, P.R. China
| | - Qingsong Xu
- School of Mathematics and Statistics, Central South University Changsha, Hunan, P.R. China
| | - Man-Lai Tang
- Department of Mathematics and Statistics, Hang Seng University of Hong Kong, Hong Kong, P.R. China
| | - Hong Wang
- School of Mathematics and Statistics, Central South University Changsha, Hunan, P.R. China
| |
Collapse
|