{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:26:39Z","timestamp":1787163999533,"version":"build-2736575974"},"reference-count":38,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Despite advances in understanding and treating non\u2013ST-elevation acute coronary syndrome (NSTE-ACS), patients continue to experience high rates of adverse outcomes, particularly those with non\u2013ST-segment elevation myocardial infarction, which remains a leading cause of cardiovascular mortality. Existing risk models may not fully reflect contemporary patient populations due to substantial changes in clinical profiles. Developing new machine learning (ML)\u2013based risk calculators may improve the prediction of in-hospital mortality (IHM) at different stages of the diagnostic process, and ultimately improve patient outcomes.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop predictive models for IHM in patients with NSTE-ACS using ML methods and predictor sets obtained during the diagnostic process.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This retrospective observational study included 1144 patients with NSTE-ACS admitted between 2019 and 2021. IHM occurred in 94 (8.1%) of 1144 patients. Predictive models were developed using multivariable logistic regression, Random Forest, XGBoost (Extreme Gradient Boosting), and CatBoost algorithms. Model performance was evaluated using the area under the receiver operating characteristic curve (ROC-AUC), area under the precision-recall curve, calibration metrics, and decision curve analysis.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A key feature of the developed models was their applicability at different stages of the diagnostic process, using predictors available at each specific stage. At admission, ML models achieved ROC-AUC values up to 0.93. After incorporating laboratory and echocardiographic data, predictive performance increased to ROC-AUC values of 0.94 to 0.95. The best-performing model demonstrated an ROC-AUC of 0.951 (95% CI 0.946\u20100.956), a sensitivity of 0.902 (95% CI 0.889\u20100.916), and a specificity of 0.891 (95% CI 0.886\u20100.896). The area under the precision-recall curve reached 0.685, and the Brier score was 0.0331, indicating good calibration. Random Forest models demonstrated greater clinical utility than the Global Registry of Acute Coronary Events score (\n P<\/jats:italic>\n <.001). Shapley Additive Explanations analysis identified the most significant predictors of mortality risk, including Killip class of acute heart failure, age, Charlson comorbidity index, creatinine level, and hematocrit level.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n ML-based models enabled accurate prediction of IHM in patients with NSTE-ACS at different stages of the diagnostic process and may improve risk stratification and clinical decision-making in real-world practice.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/89242","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:43:12Z","timestamp":1787161392000},"page":"e89242-e89242","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning\u2013Based Risk Prediction of In-Hospital Mortality in Patients With Non\u2013ST-Elevation Acute Coronary Syndrome at Various Stages of the Diagnostic Process: Observational Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4358-7329","authenticated-orcid":false,"given":"Vyacheslav V","family":"Ryabov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1513-2087","authenticated-orcid":false,"given":"Anastasiia K","family":"Nesova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7696-1666","authenticated-orcid":false,"given":"Andrey A","family":"Vishnevskiy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4539-685X","authenticated-orcid":false,"given":"Karina I","family":"Shakhgeldyan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9250-557X","authenticated-orcid":false,"given":"Boris I","family":"Geltser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"R1","unstructured":"SWEDEHEART annual report 2024. SWEDEHEART. Oct 15, 2025. URL: https:\/\/www.ucr.uu.se\/swedeheart\/dokument-sh\/arsrapporter-sh\/arsrapport-2024\/01-swedeheart-annual-report-2024-english-2\/viewdocument\/3703 [Accessed 03-08-2026]"},{"issue":"10440","key":"R2","doi-asserted-by":"publisher","first-page":"2100","DOI":"10.1016\/S0140-6736(24)00367-2","article-title":"Global burden of 288 causes of death and life expectancy decomposition in 204 countries and territories and 811 subnational locations, 1990\u20132021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"403","author":"Naghavi","journal-title":"The Lancet"},{"issue":"4","key":"R3","doi-asserted-by":"publisher","first-page":"6","DOI":"10.38109\/2225-1685-2021-4-6-59","article-title":"Eurasian clinical guidelines for the diagnosis and treatment of non-ST-segment elevation acute coronary syndrome (NSTE-ACS)","author":"Barbarash","journal-title":"Evrazijskij kardiologi\u010deskij \u017eurnal"},{"issue":"3","key":"R4","doi-asserted-by":"publisher","first-page":"88","DOI":"10.29001\/2073-8552-2017-32-3-88-94","article-title":"Approaches to diagnosis and treatment of patients with non-STsegment elevation acute coronary syndrome in Russian hospitals. Record-3 Registry Data","volume":"32","author":"Barbarash","journal-title":"Sib med \u017e (Tomsk)"},{"issue":"9","key":"R5","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2019-032165","article-title":"Evaluation of the impact of the GRACE risk score on the management and outcome of patients hospitalised with non-ST elevation acute coronary syndrome in the UK: protocol of the UKGRIS cluster-randomised registry-based trial","volume":"9","author":"Everett","journal-title":"BMJ Open"},{"issue":"4","key":"R6","doi-asserted-by":"publisher","first-page":"5843","DOI":"10.15829\/1560-4071-2024-5843","article-title":"Particularities of the course and treatment of non-ST elevation acute myocardial infarction: data from the REGION-IM registry","volume":"29","author":"Boytsov","journal-title":"Russ J Cardiol"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.ccl.2017.08.003","article-title":"Non-ST-segment acute coronary syndromes","volume":"36","author":"Hedayati","journal-title":"Cardiol Clin"},{"issue":"5","key":"R8","doi-asserted-by":"publisher","DOI":"10.1007\/s11886-019-1125-9","article-title":"Revascularization strategies for non-ST-elevation myocardial infarction","volume":"21","author":"George","journal-title":"Curr Cardiol Rep"},{"issue":"38","key":"R9","doi-asserted-by":"publisher","first-page":"3720","DOI":"10.1093\/eurheartj\/ehad191","article-title":"2023 ESC Guidelines for the management of acute coronary syndromes","volume":"44","author":"Byrne","journal-title":"Eur Heart J"},{"issue":"6","key":"R10","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1017\/S1049023X23006490","article-title":"Comparing TIMI, HEART, and GRACE risk scores to predict angiographic severity of coronary artery disease and 30-day major adverse cardiac events in emergency department patients with NSTEACS","volume":"38","author":"Yalcin Ocak","journal-title":"Prehosp Disaster med"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","DOI":"10.1186\/s12872-022-03025-6","article-title":"The prognostic utility of GRACE risk score in predictive adverse cardiovascular outcomes in patients with NSTEMI and multivessel disease","volume":"22","author":"Chen","journal-title":"BMC Cardiovasc Disord"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1186\/s12872-021-02311-z","article-title":"Comparison of GRACE and TIMI risk scores in the prediction of in-hospital and long-term outcomes among East Asian non-ST-elevation myocardial infarction patients","volume":"22","author":"Yanqiao","journal-title":"BMC Cardiovasc Disord"},{"issue":"9","key":"R13","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1093\/eurheartj\/ehi187","article-title":"TIMI, PURSUIT, and GRACE risk scores: sustained prognostic value and interaction with revascularization in NSTE-ACS","volume":"26","author":"de Ara\u00fajo Gon\u00e7alves","journal-title":"Eur Heart J"},{"issue":"11","key":"R14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0007947","article-title":"Does simplicity compromise accuracy in ACS risk prediction? A retrospective analysis of the TIMI and GRACE risk scores","volume":"4","author":"Aragam","journal-title":"PLoS One"},{"issue":"7","key":"R15","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1136\/heartjnl-2022-321470","article-title":"Role and relevance of risk stratification models in the modern-day management of non-ST elevation acute coronary syndromes","volume":"109","author":"Balasubramanian","journal-title":"Heart"},{"issue":"4","key":"R16","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/s00392-023-02258-5","article-title":"GRACE scores or high-sensitivity troponin for timing of coronary angiography in non-ST-elevation acute coronary syndromes","volume":"113","author":"Jobs","journal-title":"Clin Res Cardiol"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","first-page":"12886","DOI":"10.1038\/s41598-021-92362-1","article-title":"Machine learning enhances the performance of short and long-term mortality prediction model in non-ST-segment elevation myocardial infarction","volume":"11","author":"Lee","journal-title":"Sci Rep"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2024.1402503","article-title":"Machine learning-based prediction of mortality in acute myocardial infarction with cardiogenic shock","volume":"11","author":"Zhang","journal-title":"Front Cardiovasc Med"},{"issue":"8","key":"R19","doi-asserted-by":"publisher","first-page":"4226","DOI":"10.3390\/app15084226","article-title":"Prediction of in-hospital mortality in non-ST-segment elevation myocardial infarction, based on interpretable machine learning","volume":"15","author":"Cao","journal-title":"Applied Sciences"},{"issue":"11","key":"R20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0336130","article-title":"Mortality risk prediction in NSTE-ACS following PCI: insights from a real-world cohort","volume":"20","author":"Geng","journal-title":"PLoS ONE"},{"key":"R21","unstructured":"Ryabov VV Nesova AK . Certificate of State Registration of the Database No. 2023622190 Russian Federation. Clinical, anamnestic and instrumental characteristics of patients with NSTE-ACS for the period 2015-2022. Federal State Budgetary Scientific Institution \u201cTomsk National Research Medical Center of the Russian Academy of Sciences\u201d; 2023. URL: https:\/\/elibrary.ru\/item.asp?id=54197457 [Accessed 27-07-2026]"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2024.109370","article-title":"A review of explainable artificial intelligence in healthcare","volume":"118","author":"Sadeghi","journal-title":"Comput Electr Eng"},{"issue":"15","key":"R23","doi-asserted-by":"publisher","DOI":"10.21037\/atm.2018.07.02","article-title":"Decision curve analysis: a technical note","volume":"6","author":"Zhang","journal-title":"Ann Transl Med"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1016\/j.gloepi.2025.100242","article-title":"On misconceptions about the Brier score in binary prediction models","volume":"11","author":"Hoessly","journal-title":"Glob Epidemiol"},{"issue":"8","key":"R25","doi-asserted-by":"publisher","DOI":"10.3390\/biomedicines12081736","article-title":"Current management of non-ST-segment elevation acute coronary syndrome","volume":"12","author":"D\u00edez-Villanueva","journal-title":"Biomedicines"},{"issue":"2","key":"R26","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-044329","article-title":"Demographics, practice patterns and long-term outcomes of patients with non-ST-segment elevation acute coronary syndrome in the past two decades: the CREDO-Kyoto Cohort-2 and Cohort-3","volume":"11","author":"Takeji","journal-title":"BMJ Open"},{"issue":"20","key":"R27","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1136\/hrt.2010.198804","article-title":"The Swedish Web-system for enhancement and development of evidence-based care in heart disease evaluated according to recommended therapies (SWEDEHEART)","volume":"96","author":"Jernberg","journal-title":"Heart"},{"issue":"Suppl B","key":"R28","doi-asserted-by":"publisher","first-page":"B3","DOI":"10.1093\/eurheartjsupp\/suac001","article-title":"Patient characteristics, treatment strategy, outcomes, and hospital costs of acute coronary syndrome: 3 years of data from a large high-volume centre in Central Europe","volume":"24","author":"Tou\u0161ek","journal-title":"Eur Heart J Suppl"},{"issue":"4","key":"R29","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1093\/ehjqcco\/qcy002","article-title":"Use of clinical risk stratification in non-ST elevation acute coronary syndromes: an analysis from the CONCORDANCE registry","volume":"4","author":"Bing","journal-title":"Eur Heart J Qual Care Clin Outcomes"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/21548331.2020.1701329","article-title":"Contemporary NSTEMI management: the role of the hospitalist","volume":"48","author":"Pollack","journal-title":"Hosp Pract"},{"issue":"5","key":"R31","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1177\/2048872616647705","article-title":"Excess mortality and guideline-indicated care following non-ST-elevation myocardial infarction","volume":"6","author":"Dondo","journal-title":"Eur Heart J Acute Cardiovasc Care"},{"issue":"4","key":"R32","doi-asserted-by":"publisher","DOI":"10.2174\/1573403X16999201210195702","article-title":"Myocardial infarction with and without ST-segment elevation: a contemporary reappraisal of similarities and differences","volume":"17","author":"Mitsis","journal-title":"Curr Cardiol Rev"},{"issue":"42","key":"R33","doi-asserted-by":"publisher","first-page":"3807","DOI":"10.1093\/eurheartj\/ehy577","article-title":"Treatment-risk paradox in acute coronary syndromes","volume":"39","author":"Roffi","journal-title":"Eur Heart J"},{"issue":"4","key":"R34","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1002\/clc.23781","article-title":"Immediate and early percutaneous coronary intervention in very high-risk and high-risk non-ST segment elevation myocardial infarction patients","volume":"45","author":"Lupu","journal-title":"Clin Cardiol"},{"key":"R35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.107953","article-title":"Interpretable machine learning for in-hospital mortality risk prediction in patients with ST-elevation myocardial infarction after percutaneous coronary interventions","volume":"170","author":"Shakhgeldyan","journal-title":"Comput Biol Med"},{"issue":"2","key":"R36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0298036","article-title":"Data analytics approach for short- and long-term mortality prediction following acute non-ST-elevation myocardial infarction (NSTEMI) and Unstable Angina (UA) in Asians","volume":"19","author":"Kasim","journal-title":"PLoS One"},{"issue":"10","key":"R37","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0224502","article-title":"Deep-learning-based risk stratification for mortality of patients with acute myocardial infarction","volume":"14","author":"Kwon","journal-title":"PLoS One"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","first-page":"13393","DOI":"10.1038\/s41598-024-64048-x","article-title":"Development and validation of a machine learning-based readmission risk prediction model for non-ST elevation myocardial infarction patients after percutaneous coronary intervention","volume":"14","author":"Liu","journal-title":"Sci Rep"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T17:43:14Z","timestamp":1787161394000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e89242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.2196\/89242","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]},"article-number":"v14i10440e89242"}}