1
|
Yao L, Rey DA, Bulgarelli L, Kast R, Osborn J, Van Ark E, Fang LT, Lau B, Lam H, Teixeira LM, Neto AS, Bellomo R, Deliberato RO. Gene Expression Scoring of Immune Activity Levels for Precision Use of Hydrocortisone in Vasodilatory Shock. Shock 2022; 57:384-391. [PMID: 35081076 PMCID: PMC8868213 DOI: 10.1097/shk.0000000000001910] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2021] [Revised: 12/06/2021] [Accepted: 01/07/2022] [Indexed: 11/26/2022]
Abstract
PURPOSE Among patients with vasodilatory shock, gene expression scores may identify different immune states. We aimed to test whether such scores are robust in identifying patients' immune state and predicting response to hydrocortisone treatment in vasodilatory shock. MATERIALS AND METHODS We selected genes to generate continuous scores to define previously established subclasses of sepsis. We used these scores to identify a patient's immune state. We evaluated the potential for these states to assess the differential effect of hydrocortisone in two randomized clinical trials of hydrocortisone versus placebo in vasodilatory shock. RESULTS We initially identified genes associated with immune-adaptive, immune-innate, immune-coagulant functions. From these genes, 15 were most relevant to generate expression scores related to each of the functions. These scores were used to identify patients as immune-adaptive prevalent (IA-P) and immune-innate prevalent (IN-P). In IA-P patients, hydrocortisone therapy increased 28-day mortality in both trials (43.3% vs 14.7%, P = 0.028) and (57.1% vs 0.0%, P = 0.99). In IN-P patients, this effect was numerically reversed. CONCLUSIONS Gene expression scores identified the immune state of vasodilatory shock patients, one of which (IA-P) identified those who may be harmed by hydrocortisone. Gene expression scores may help advance the field of personalized medicine.
Collapse
Affiliation(s)
- Lijing Yao
- Department of Clinical Data Science, Endpoint Health Inc, Palo Alto, California
| | - Diego Ariel Rey
- Department of Clinical Data Science, Endpoint Health Inc, Palo Alto, California
| | - Lucas Bulgarelli
- Department of Clinical Data Science, Endpoint Health Inc, Palo Alto, California
| | - Rachel Kast
- Department of Clinical Data Science, Endpoint Health Inc, Palo Alto, California
| | - Jeff Osborn
- Department of Clinical Data Science, Endpoint Health Inc, Palo Alto, California
| | - Emily Van Ark
- Department of Clinical Data Science, Endpoint Health Inc, Palo Alto, California
| | - Li Tai Fang
- Department of Clinical Data Science, Endpoint Health Inc, Palo Alto, California
| | - Bayo Lau
- Bioinformatics Department, HypaHub Inc, San Jose, California, USA
| | - Hugo Lam
- Bioinformatics Department, HypaHub Inc, San Jose, California, USA
| | | | - Ary Serpa Neto
- Department of Critical Care Medicine, Hospital Israelita Albert Einstein, São Paulo, Brazil
- Australian and New Zealand Intensive Care Research Centre (ANZIC-RC), School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia
- Department of Critical Care, Melbourne Medical School, University of Melbourne, Austin Hospital, Melbourne, Australia
- Data Analytics Research and Evaluation (DARE) Centre, Austin Hospital, Melbourne, Australia
| | - Rinaldo Bellomo
- Australian and New Zealand Intensive Care Research Centre (ANZIC-RC), School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia
- Department of Critical Care, Melbourne Medical School, University of Melbourne, Austin Hospital, Melbourne, Australia
- Data Analytics Research and Evaluation (DARE) Centre, Austin Hospital, Melbourne, Australia
- Department of Intensive Care, Austin Hospital, Melbourne, Australia
- Department of Intensive Care, Royal Melbourne Hospital, Melbourne, Australia
| | | |
Collapse
|
2
|
Zhao Y, Jia L, Jia R, Han H, Feng C, Li X, Wei Z, Wang H, Zhang H, Pan S, Wang J, Guo X, Yu Z, Li X, Wang Z, Chen W, Li J, Li T. A New Time-Window Prediction Model For Traumatic Hemorrhagic Shock Based on Interpretable Machine Learning. Shock 2022; 57:48-56. [PMID: 34905530 PMCID: PMC8663521 DOI: 10.1097/shk.0000000000001842] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2021] [Accepted: 07/26/2021] [Indexed: 12/29/2022]
Abstract
ABSTRACT Early warning prediction of traumatic hemorrhagic shock (THS) can greatly reduce patient mortality and morbidity. We aimed to develop and validate models with different stepped feature sets to predict THS in advance. From the PLA General Hospital Emergency Rescue Database and Medical Information Mart for Intensive Care III, we identified 604 and 1,614 patients, respectively. Two popular machine learning algorithms (i.e., extreme gradient boosting [XGBoost] and logistic regression) were applied. The area under the receiver operating characteristic curve (AUROC) was used to evaluate the performance of the models. By analyzing the feature importance based on XGBoost, we found that features in vital signs (VS), routine blood (RB), and blood gas analysis (BG) were the most relevant to THS (0.292, 0.249, and 0.225, respectively). Thus, the stepped relationships existing in them were revealed. Furthermore, the three stepped feature sets (i.e., VS, VS + RB, and VS + RB + sBG) were passed to the two machine learning algorithms to predict THS in the subsequent T hours (where T = 3, 2, 1, or 0.5), respectively. Results showed that the XGBoost model performance was significantly better than the logistic regression. The model using vital signs alone achieved good performance at the half-hour time window (AUROC = 0.935), and the performance was increased when laboratory results were added, especially when the time window was 1 h (AUROC = 0.950 and 0.968, respectively). These good-performing interpretable models demonstrated acceptable generalization ability in external validation, which could flexibly and rollingly predict THS T hours (where T = 0.5, 1) prior to clinical recognition. A prospective study is necessary to determine the clinical utility of the proposed THS prediction models.
Collapse
Affiliation(s)
- Yuzhuo Zhao
- Department of Emergency, The First Medical Center of Chinese PLA General Hospital, Beijing, China
| | - Lijing Jia
- Department of Emergency, The First Medical Center of Chinese PLA General Hospital, Beijing, China
| | - Ruiqi Jia
- School of Economics and Management, Beijing Jiaotong University, Beijing, China
| | - Hui Han
- Department of Emergency, The First Medical Center of Chinese PLA General Hospital, Beijing, China
| | - Cong Feng
- Department of Emergency, The First Medical Center of Chinese PLA General Hospital, Beijing, China
| | - Xueyan Li
- Management School, Beijing Union University, Beijing, China
| | | | - Hongxin Wang
- Department of Emergency, Armed Police Characteristic Medical Center, Tianjin, China
| | - Heng Zhang
- Department of Emergency, The First Medical Center of Chinese PLA General Hospital, Beijing, China
| | - Shuxiao Pan
- College of Computer Science and Artificial Intelligence, Wenzhou University
| | - Jiaming Wang
- School of Economics and Management, Beijing Jiaotong University, Beijing, China
| | - Xin Guo
- Beijing Friendship Hospital, Capital Medical University, Beijing, China
| | - Zheyuan Yu
- School of Economics and Management, Beijing Jiaotong University, Beijing, China
| | - Xiucheng Li
- School of Economics and Management, Beijing Jiaotong University, Beijing, China
| | - Zhaohong Wang
- School of Economics and Management, Beijing Jiaotong University, Beijing, China
| | - Wei Chen
- Department of Emergency, The Third Medical Center of Chinese PLA General Hospital, Beijing, China
- Hainan Hospital of Chinese PLA General Hospital, Sanya, China
| | - Jing Li
- School of Economics and Management, Beijing Jiaotong University, Beijing, China
| | - Tanshi Li
- Department of Emergency, The First Medical Center of Chinese PLA General Hospital, Beijing, China
| |
Collapse
|
3
|
Tsondai PR, Davies MA, Singtoroj T, Maxwell N, McGowan CC, Songtaweesin WN, Technau KG, Kariminia A, Chimbetete C, Succi RCM, Pinto J, Rouzier V, Luque MT, Sohn AH; IeDEA Consortium. Improving Methods to Classify Perinatal versus Nonperinatal HIV Acquisition in Young Adolescents 10-14 Years of Age. Pediatr Infect Dis J 2021; 40:453-6. [PMID: 33538538 DOI: 10.1097/INF.0000000000003059] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
Mode of HIV acquisition for adolescents with HIV is often not recorded within routine healthcare databases. Hence, age at enrollment in HIV care is often used as a proxy for perinatal versus nonperinatal infection. Using routine cohort data from adolescents presenting for HIV care 10-14 years of age, we developed logistic regression models to predict likely mode of infection.
Collapse
|
4
|
Gara N, Zhao X, Kleiner DE, Liang TJ, Hoofnagle JH, Ghany MG. Discordance among transient elastography, aspartate aminotransferase to platelet ratio index, and histologic assessments of liver fibrosis in patients with chronic hepatitis C. Clin Gastroenterol Hepatol 2013; 11:303-8.e1. [PMID: 23142332 PMCID: PMC3642246 DOI: 10.1016/j.cgh.2012.10.044] [Citation(s) in RCA: 22] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/02/2012] [Revised: 10/02/2012] [Accepted: 10/26/2012] [Indexed: 02/07/2023]
Abstract
BACKGROUND & AIMS Liver biopsy is the standard for assessing hepatic fibrosis. Ultrasound transient elastography (TE) and the aspartate aminotransferase to platelet ratio index (APRI) are validated, noninvasive tests for identifying patients with cirrhosis. We evaluated discordance among TE, APRI, and histology diagnoses of cirrhosis. METHODS We analyzed findings from 109 patients with chronic hepatitis C who underwent TE within 6 months of liver biopsy at the US National Institutes of Health from 2006 to 2011. Fibrosis was scored using the Ishak scale (0-6). APRI scores were calculated using data collected on the day of the biopsy. Area under receiver operator characteristic curves for TE and APRI were calculated to distinguish patients with cirrhosis (Ishak scores, 5-6) from those without cirrhosis (Ishak scores, 0-4). The best cut-off value and corresponding positive predictive value (PPV) and negative predictive value (NPV) were selected. RESULTS Based on biopsy analysis, 18% of the patients had no fibrosis, 52% had mild fibrosis, 17% had bridging fibrosis, and 13% had cirrhosis. A TE cut-off value of 13.1 kPa identified patients with cirrhosis with the highest level of accuracy (100% sensitivity, 89% specificity, 58% PPV, 100% NPV), as did an APRI cut-off value of 1.0 (79% sensitivity, 78% specificity, 34% PPV, 96% NPV). Results from TE and APRI were discordant for 28% of cases. TE identified all cases of cirrhosis and an additional 10 patients who were not found to have cirrhosis based on histology analysis; 7 of these patients had clinical or radiologic evidence of cirrhosis, indicating that the biopsy sample was not staged correctly. CONCLUSIONS TE increases the accuracies of biopsy and APRI analyses in identifying patients with cirrhosis. TE also might be used to screen patients for cirrhosis and identify those who should be followed up for development of hepatocellular carcinoma and varices.
Collapse
Affiliation(s)
- Naveen Gara
- Liver Diseases Branch, National Institute of Diabetes and Digestive and Kidney Diseases, National Institutes of Health, Bethesda, Maryland 20892, USA.
| | - Xiongce Zhao
- Biostatistics, Intramural Research, National Institute of Diabetes and Digestive and Kidney Diseases, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - David E. Kleiner
- Laboratory of Pathology, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - T. Jake Liang
- Liver Diseases Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Jay H. Hoofnagle
- Liver Diseases Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| | - Marc G. Ghany
- Liver Diseases Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland
| |
Collapse
|