{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:10:11Z","timestamp":1792512611815,"version":"4.5.0"},"reference-count":42,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"\n Background<\/jats:title>\n Accurate mortality risk prediction is crucial for effective cardiovascular risk management. Recent advancements in artificial intelligence (AI) have demonstrated potential in this specific medical field. Qwen-2 and Llama-3 are high-performance, open-source large language models (LLMs) available online. An artificial neural network (ANN) algorithm derived from the SWEDEHEART (Swedish Web System for Enhancement and Development of Evidence-Based Care in Heart Disease Evaluated According to Recommended Therapies) registry, termed SWEDEHEART-AI, can predict patient prognosis following acute myocardial infarction (AMI).<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to evaluate the 3 models mentioned above in predicting 1-year all-cause mortality in critically ill patients with AMI.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n The Medical Information Mart for Intensive Care IV (MIMIC-IV) database is a publicly available data set in critical care medicine. We included 2758 patients who were first admitted for AMI and discharged alive. SWEDEHEART-AI calculated the mortality rate based on each patient\u2019s 21 clinical variables. Qwen-2 and Llama-3 analyzed the content of patients\u2019 discharge records and directly provided a 1-decimal value between 0 and 1 to represent 1-year death risk probabilities. The patients\u2019 actual mortality was verified using follow-up data. The predictive performance of the 3 models was assessed and compared using the Harrell C-statistic (C-index), the area under the receiver operating characteristic curve (AUROC), calibration plots, Kaplan-Meier curves, and decision curve analysis.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n SWEDEHEART-AI demonstrated strong discrimination in predicting 1-year all-cause mortality in patients with AMI, with a higher C-index than Qwen-2 and Llama-3 (C-index 0.72, 95% CI 0.69-0.74 vs C-index 0.65, 0.62-0.67 vs C-index 0.56, 95% CI 0.53-0.58, respectively; all P<.001 for both comparisons). SWEDEHEART-AI also showed high and consistent AUROC in the time-dependent ROC curve. The death rates calculated by SWEDEHEART-AI were positively correlated with actual mortality, and the 3 risk classes derived from this model showed clear differentiation in the Kaplan-Meier curve (P<.001). Calibration plots indicated that SWEDEHEART-AI tended to overestimate mortality risk, with an observed-to-expected ratio of 0.478. Compared with the LLMs, SWEDEHEART-AI demonstrated positive and greater net benefits at risk thresholds below 19%.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n SWEDEHEART-AI, a trained ANN model, demonstrated the best performance, with strong discrimination and clinical utility in predicting 1-year all-cause mortality in patients with AMI from an intensive care cohort. Among the LLMs, Qwen-2 outperformed Llama-3 and showed moderate predictive value. Qwen-2 and SWEDEHEART-AI exhibited comparable classification effectiveness. The future integration of LLMs into clinical decision support systems holds promise for accurate risk stratification in patients with AMI; however, further research is needed to optimize LLM performance and address calibration issues across diverse patient populations.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/67253","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T11:45:49Z","timestamp":1747050349000},"page":"e67253","source":"Crossref","is-referenced-by-count":17,"title":["Large Language Models and Artificial Neural Networks for Assessing 1-Year Mortality in Patients With Myocardial Infarction: Analysis From the Medical Information Mart for Intensive Care IV (MIMIC-IV) Database"],"prefix":"10.2196","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3403-9128","authenticated-orcid":false,"given":"Boqun","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4276-9068","authenticated-orcid":false,"given":"Liangguo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9817-2327","authenticated-orcid":false,"given":"Shuo","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7676-3846","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7321-6211","authenticated-orcid":false,"given":"Shen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5946-3018","authenticated-orcid":false,"given":"Fadong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4842-3292","authenticated-orcid":false,"given":"Wenxin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5944-3194","authenticated-orcid":false,"given":"Pengrong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8024-2161","authenticated-orcid":false,"given":"Leli","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0567-7883","authenticated-orcid":false,"given":"Chu","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8126-2356","authenticated-orcid":false,"given":"Yi","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4265-4240","authenticated-orcid":false,"given":"Xiaofan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehx515"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2021.08.018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(21)00228-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-024-02045-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232756"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae045"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2196\/54580"},{"key":"ref9","unstructured":"GitHub2025-05-01https:\/\/qwenlm.github.io\/blog\/qwen2\/"},{"key":"ref10","unstructured":"AI at Meta2025-05-01https:\/\/ai.meta.com\/blog\/meta-llama-3\/"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.g7594"},{"key":"ref13","unstructured":"Ollama2025-05-01https:\/\/ollama.com\/"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1093\/ejcts\/ezy180"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2015.02.010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2848"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2015.37"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2020.11.010"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2023.06.025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-023-01925-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-023-03284-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2024.05.022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.231147"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00989-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1814259"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/1460458219871780"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjcard.2020.07.048"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2021.0122"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)32519-8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.122.025812"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(19)30037-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.01.013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1287541"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-46411-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01302-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X211044697"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.121.007858"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11883-024-01210-w"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1055\/s-0039-1697949"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00873-0"},{"key":"ref42","unstructured":"PhysioNet2025-05-01https:\/\/physionet.org\/content\/mimiciv\/2.2\/"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2025\/1\/e67253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T14:00:09Z","timestamp":1785852009000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2025\/1\/e67253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,12]]},"references-count":42,"URL":"https:\/\/doi.org\/10.2196\/67253","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.67253","asserted-by":"object"}]},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,12]]}}}