{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:51:26Z","timestamp":1791827486280,"version":"4.3.4"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Department-level Project of Jiangsu Provincial Hospital of Traditional Chinese Medicine","award":["K25092"],"award-info":[{"award-number":["K25092"]}],"id":[{"id":"https:\/\/ror.org\/05sm6p196","id-type":"ROR","asserted-by":"crossref"}]},{"name":"the Postgraduate Research & Practice Innovation Program of Jiangsu Province","award":["SJX25-1001"],"award-info":[{"award-number":["SJX25-1001"]}]},{"name":"the Natural Science Foundation of Nanjing University of Chinese Medicine","award":["XZR2023002"],"award-info":[{"award-number":["XZR2023002"]}],"id":[{"id":"https:\/\/ror.org\/04523zj19","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Science and Technology Program of Bureau of Traditional Chinese Medicine of Jiangsu Province","award":["ms2021008"],"award-info":[{"award-number":["ms2021008"]}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Sepsis-related myocardial injury (SRMI) is associated with high mortality, but the transportability of prediction models across heterogeneous cohorts remains uncertain. We developed and externally validated a machine learning model for in-hospital mortality prediction in SRMI and evaluated its discrimination, calibration, interpretability, and distributional shift across cohorts. Using MIMIC-IV for development and MIMIC-III and a local cohort for external validation (n\u2009=\u20091,226, 962, and 280, respectively), we compared eight classification algorithms. A two-stage feature-selection strategy, recursive feature accumulation and sequential elimination with incremental feature evaluation, ranked 31 candidate variables to derive a parsimonious predictor set. The selected model was evaluated for discrimination, precision-recall performance, calibration, clinical utility, and risk stratification. Logistic recalibration, population stability index (PSI) analysis, and SHapley Additive exPlanations (SHAP) were used to assess probability alignment, cross-cohort distributional shift, and model interpretability. Feature selection reduced 31 candidate variables to 8 predictors with little loss of cross-validated performance (AUC, 0.819 with 31 variables versus 0.810 with 8 variables). The selected random forest model achieved an AUC of 0.819 (bootstrap 95% CI, 0.787-0.848) and a PR-AUC of 0.702 (0.657-0.751) in MIMIC-III, and an AUC of 0.758 (0.693-0.816) and a PR-AUC of 0.525 (0.435-0.630) in the local cohort. Recalibration reduced the Brier score from 0.162 to 0.147 in MIMIC-III and from 0.233 to 0.196 in the local cohort. PSI indicated minimal distributional shift between MIMIC-IV and MIMIC-III but substantial shift in the local cohort, particularly for SOFA score, respiratory rate, and prothrombin time. SHAP identified prothrombin time, invasive ventilation, lactate, temperature, and urine output as major contributors to model predictions. In two external cohorts, an 8-variable random forest model showed moderate discrimination for mortality prediction in SRMI. The evaluation of external performance, calibration, distributional shift, and SHAP-based explanations provides an assessment of model transportability. Prospective validation is needed before clinical deployment.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001758","type":"journal-article","created":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:28:36Z","timestamp":1791826116000},"page":"e0001758","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["A machine learning model for in-hospital mortality prediction in patients with sepsis-related myocardial injury"],"prefix":"10.1371","volume":"5","author":[{"given":"Da-cheng","family":"Wang","sequence":"first","affiliation":[{"name":"Affiliated Hospital of Nanjing University of Chinese Medicine","place":["Nanjing, Jiangsu, China"],"department":["Department of Intensive Care Unit"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan-pin","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University of Chinese Medicine","place":["Nanjing, Jiangsu, China"],"department":["The First Clinical Medical College"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-ting","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University of Chinese Medicine","place":["Nanjing, Jiangsu, China"],"department":["The First Clinical Medical College"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-huan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Nanjing University of Chinese Medicine","place":["Nanjing, Jiangsu, China"],"department":["The First Clinical Medical College"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-peng","family":"Yin","sequence":"additional","affiliation":[{"name":"Nanjing University of Chinese Medicine","place":["Nanjing, Jiangsu, China"],"department":["The First Clinical Medical College"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin-yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University of Chinese Medicine","place":["Nanjing, Jiangsu, China"],"department":["The First Clinical Medical College"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6286-1621","authenticated-orcid":true,"given":"Yan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Affiliated Hospital of Nanjing University of Chinese Medicine","place":["Nanjing, Jiangsu, China"],"department":["Department of Intensive Care Unit"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,12]]},"reference":[{"issue":"8","key":"pdig.0001758.ref001","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1001\/jama.2016.0287","article-title":"The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3)","volume":"315","author":"M Singer","year":"2016","journal-title":"JAMA"},{"issue":"10141","key":"pdig.0001758.ref002","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/S0140-6736(18)30696-2","article-title":"Sepsis and septic shock","volume":"392","author":"M Cecconi","year":"2018","journal-title":"Lancet"},{"issue":"10219","key":"pdig.0001758.ref003","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/S0140-6736(19)32989-7","article-title":"Global, regional, and national sepsis incidence and mortality, 1990-2017: analysis for the Global Burden of Disease Study","volume":"395","author":"KE Rudd","year":"2020","journal-title":"Lancet"},{"issue":"4","key":"pdig.0001758.ref004","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1097\/CCM.0000000000002851","article-title":"Septic Cardiomyopathy","volume":"46","author":"SJ Beesley","year":"2018","journal-title":"Crit Care Med"},{"issue":"6","key":"pdig.0001758.ref005","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1038\/s41569-020-00492-2","article-title":"Pathophysiology of sepsis-induced cardiomyopathy","volume":"18","author":"SM Hollenberg","year":"2021","journal-title":"Nat Rev Cardiol"},{"issue":"2","key":"pdig.0001758.ref006","doi-asserted-by":"crossref","DOI":"10.1161\/CIRCOUTCOMES.117.004040","article-title":"Myocardial Injury in Patients With Sepsis and Its Association With Long-Term Outcome","volume":"11","author":"JF Frencken","year":"2018","journal-title":"Circ Cardiovasc Qual Outcomes"},{"issue":"7","key":"pdig.0001758.ref007","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1016\/j.mayocp.2012.01.018","article-title":"Clinical spectrum, frequency, and significance of myocardial dysfunction in severe sepsis and septic shock","volume":"87","author":"JN Pulido","year":"2012","journal-title":"Mayo Clin Proc"},{"issue":"1","key":"pdig.0001758.ref008","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1186\/s13054-025-05249-2","article-title":"Early high-sensitivity troponin elevation and short-term mortality in sepsis: a systematic review with meta-analysis","volume":"29","author":"AIJ Gajardo","year":"2025","journal-title":"Crit Care"},{"issue":"1","key":"pdig.0001758.ref009","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1186\/s12871-023-02189-8","article-title":"Predictors and nomogram of in-hospital mortality in sepsis-induced myocardial injury: a retrospective cohort study","volume":"23","author":"K-Z Xu","year":"2023","journal-title":"BMC Anesthesiol"},{"issue":"6","key":"pdig.0001758.ref010","doi-asserted-by":"crossref","first-page":"1599","DOI":"10.1097\/01.CCM.0000266683.64081.02","article-title":"Mechanisms of sepsis-induced cardiac dysfunction","volume":"35","author":"A Rudiger","year":"2007","journal-title":"Crit Care Med"},{"issue":"6","key":"pdig.0001758.ref011","doi-asserted-by":"crossref","first-page":"227","DOI":"10.3892\/mmr.2023.13114","article-title":"Sepsis\u2011induced cardiac dysfunction and pathogenetic mechanisms (Review)","volume":"28","author":"J Song","year":"2023","journal-title":"Mol Med Rep"},{"issue":"9","key":"pdig.0001758.ref012","doi-asserted-by":"crossref","first-page":"4710","DOI":"10.3390\/ijms25094710","article-title":"Current Perspectives of Mitochondria in Sepsis-Induced Cardiomyopathy","volume":"25","author":"T Kuroshima","year":"2024","journal-title":"Int J Mol Sci"},{"issue":"1","key":"pdig.0001758.ref013","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1186\/s13054-024-05069-w","article-title":"Mitochondrial dysfunction in sepsis: mechanisms and therapeutic perspectives","volume":"28","author":"D Hu","year":"2024","journal-title":"Crit Care"},{"issue":"3","key":"pdig.0001758.ref014","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1001\/jama.2016.20328","article-title":"Prognostic Accuracy of the SOFA Score, SIRS Criteria, and qSOFA Score for In-Hospital Mortality Among Adults With Suspected Infection Admitted to the Intensive Care Unit","volume":"317","author":"EP Raith","year":"2017","journal-title":"JAMA"},{"issue":"4","key":"pdig.0001758.ref015","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1159\/000088708","article-title":"Value of APACHE II, SOFA and CPIS scores in predicting prognosis in patients with ventilator-associated pneumonia","volume":"73","author":"G Gursel","year":"2006","journal-title":"Respiration"},{"issue":"5","key":"pdig.0001758.ref016","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1378\/chest.129.5.1349","article-title":"Sepsis-associated myocardial dysfunction: diagnostic and prognostic impact of cardiac troponins and natriuretic peptides","volume":"129","author":"M Maeder","year":"2006","journal-title":"Chest"},{"issue":"7","key":"pdig.0001758.ref017","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1007\/s00134-013-2902-3","article-title":"Prognostic value of troponins in sepsis: a meta-analysis","volume":"39","author":"F Bessi\u00e8re","year":"2013","journal-title":"Intensive Care Med"},{"issue":"3","key":"pdig.0001758.ref018","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1007\/s00134-019-05872-y","article-title":"Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy","volume":"46","author":"LM Fleuren","year":"2020","journal-title":"Intensive Care Med"},{"issue":"1","key":"pdig.0001758.ref019","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1186\/s13054-024-04948-6","article-title":"A scoping review of machine learning for sepsis prediction- feature engineering strategies and model performance: a step towards explainability","volume":"28","author":"S Bomrah","year":"2024","journal-title":"Crit Care"},{"issue":"1","key":"pdig.0001758.ref020","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1186\/s12911-024-02630-z","article-title":"Prediction of sepsis mortality in ICU patients using machine learning methods","volume":"24","author":"J Gao","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"pdig.0001758.ref021","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1038\/s41746-025-01643-w","article-title":"Artificial intelligence based multispecialty mortality prediction models for septic shock in a multicenter retrospective study","volume":"8","author":"S Wang","year":"2025","journal-title":"NPJ Digit Med"},{"issue":"9","key":"pdig.0001758.ref022","article-title":"The myth of generalisability in clinical research and machine learning in health care","volume":"2","author":"J Futoma","year":"2020","journal-title":"Lancet Digit Health"},{"key":"pdig.0001758.ref023","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1186\/s40635-025-00765-5","article-title":"Explainable machine learning models for mortality prediction in ICU patients with sepsis: a retrospective observational study","volume":"13","author":"S Diwan","year":"2025","journal-title":"Intensive Care Med Exp"},{"issue":"4","key":"pdig.0001758.ref024","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1055\/s-0041-1735184","article-title":"Systematic Review of Approaches to Preserve Machine Learning Performance in the Presence of Temporal Dataset Shift in Clinical Medicine","volume":"12","author":"LL Guo","year":"2021","journal-title":"Appl Clin Inform"},{"issue":"12","key":"pdig.0001758.ref025","doi-asserted-by":"crossref","first-page":"4026","DOI":"10.3390\/jcm14124026","article-title":"Machine Learning and Artificial Intelligence in Intensive Care Medicine: Critical Recalibrations from Rule-Based Systems to Frontier Models","volume":"14","author":"P Hadweh","year":"2025","journal-title":"J Clin Med"},{"issue":"1","key":"pdig.0001758.ref026","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"AEW Johnson","year":"2023","journal-title":"Sci Data"},{"key":"pdig.0001758.ref027","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"AEW Johnson","year":"2016","journal-title":"Sci Data"},{"key":"pdig.0001758.ref028","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"I Guyon","year":"2003","journal-title":"J Mach Learn Res"},{"issue":"1","key":"pdig.0001758.ref029","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"pdig.0001758.ref030","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"SM Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"issue":"9","key":"pdig.0001758.ref031","first-page":"737","article-title":"Adult sepsis-related myocardial injury and\/or cardiac dysfunction: emergency expert consensus","volume":"45","author":"Y Li","year":"2025","journal-title":"Zhongguo Jijiu Yixue"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:28:45Z","timestamp":1791826125000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001758"}},"subtitle":[],"editor":[{"given":"Henry Horng-Shing","family":"Lu","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University","place":["TAIWAN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,12]]},"references-count":31,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001758","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,12]]}}}