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

BackgroundAccurate 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 lan...

Full description

Saved in:
Bibliographic Details
Main Authors: Boqun Shi, Liangguo Chen, Shuo Pang, Yue Wang, Shen Wang, Fadong Li, Wenxin Zhao, Pengrong Guo, Leli Zhang, Chu Fan, Yi Zou, Xiaofan Wu
Format: Article
Language:English
Published: JMIR Publications 2025-05-01
Series:Journal of Medical Internet Research
Online Access:https://www.jmir.org/2025/1/e67253
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850032301038108672
author Boqun Shi
Liangguo Chen
Shuo Pang
Yue Wang
Shen Wang
Fadong Li
Wenxin Zhao
Pengrong Guo
Leli Zhang
Chu Fan
Yi Zou
Xiaofan Wu
author_facet Boqun Shi
Liangguo Chen
Shuo Pang
Yue Wang
Shen Wang
Fadong Li
Wenxin Zhao
Pengrong Guo
Leli Zhang
Chu Fan
Yi Zou
Xiaofan Wu
author_sort Boqun Shi
collection DOAJ
description BackgroundAccurate 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). ObjectiveThis study aims to evaluate the 3 models mentioned above in predicting 1-year all-cause mortality in critically ill patients with AMI. MethodsThe 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’s 21 clinical variables. Qwen-2 and Llama-3 analyzed the content of patients’ discharge records and directly provided a 1-decimal value between 0 and 1 to represent 1-year death risk probabilities. The patients’ 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. ResultsSWEDEHEART-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%. ConclusionsSWEDEHEART-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.
format Article
id doaj-art-2a473ecfba09441884c5b3db864da5c8
institution DOAJ
issn 1438-8871
language English
publishDate 2025-05-01
publisher JMIR Publications
record_format Article
series Journal of Medical Internet Research
spelling doaj-art-2a473ecfba09441884c5b3db864da5c82025-08-20T02:58:41ZengJMIR PublicationsJournal of Medical Internet Research1438-88712025-05-0127e6725310.2196/67253Large 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) DatabaseBoqun Shihttps://orcid.org/0000-0002-3403-9128Liangguo Chenhttps://orcid.org/0009-0008-4276-9068Shuo Panghttps://orcid.org/0009-0007-9817-2327Yue Wanghttps://orcid.org/0000-0001-7676-3846Shen Wanghttps://orcid.org/0000-0002-7321-6211Fadong Lihttps://orcid.org/0009-0003-5946-3018Wenxin Zhaohttps://orcid.org/0009-0009-4842-3292Pengrong Guohttps://orcid.org/0000-0002-5944-3194Leli Zhanghttps://orcid.org/0009-0004-8024-2161Chu Fanhttps://orcid.org/0009-0005-0567-7883Yi Zouhttps://orcid.org/0009-0005-8126-2356Xiaofan Wuhttps://orcid.org/0000-0003-4265-4240 BackgroundAccurate 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). ObjectiveThis study aims to evaluate the 3 models mentioned above in predicting 1-year all-cause mortality in critically ill patients with AMI. MethodsThe 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’s 21 clinical variables. Qwen-2 and Llama-3 analyzed the content of patients’ discharge records and directly provided a 1-decimal value between 0 and 1 to represent 1-year death risk probabilities. The patients’ 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. ResultsSWEDEHEART-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%. ConclusionsSWEDEHEART-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.https://www.jmir.org/2025/1/e67253
spellingShingle Boqun Shi
Liangguo Chen
Shuo Pang
Yue Wang
Shen Wang
Fadong Li
Wenxin Zhao
Pengrong Guo
Leli Zhang
Chu Fan
Yi Zou
Xiaofan Wu
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
Journal of Medical Internet Research
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
title_full 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
title_fullStr 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
title_full_unstemmed 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
title_short 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
title_sort 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
url https://www.jmir.org/2025/1/e67253
work_keys_str_mv AT boqunshi largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT liangguochen largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT shuopang largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT yuewang largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT shenwang largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT fadongli largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT wenxinzhao largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT pengrongguo largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT lelizhang largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT chufan largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT yizou largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase
AT xiaofanwu largelanguagemodelsandartificialneuralnetworksforassessing1yearmortalityinpatientswithmyocardialinfarctionanalysisfromthemedicalinformationmartforintensivecareivmimicivdatabase