{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["29(2)"],"submitter":["Zhang X"],"pubmed_abstract":["Effective risk stratification is crucial for managing acute coronary syndrome (ACS). This study evaluated whether general-purpose large language models (LLMs) can reliably execute the complex clinical reasoning required for cardiovascular prognosis. We quantitatively assessed three LLMs-ChatGPT 4o, DeepSeek R1, and Grok 3-for predicting one-year major adverse cardiovascular events (MACEs), using 29 guideline-recommended features from 903 participants in the LM-ACS cohort and 64 participants in the MIMIC database. All models demonstrated significant risk overestimation and substantial output variability across ten independent runs. Although Grok 3 showed the highest initial accuracy, its average performance over all runs showed no significant difference. ROC analysis indicated that none of "],"journal":["iScience"],"pagination":["114644"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12874424"],"repository":["biostudies-literature"],"pubmed_title":["Large language models for predicting one-year major adverse cardiovascular events in acute coronary syndrome."],"pmcid":["PMC12874424"],"pubmed_authors":["Zheng Y","Li J","Yang K","Shang L","Lai F","Zhang X","Xu T","Hu K","Hou S","Huang R","Tian P","Su G"],"additional_accession":[]},"is_claimable":false,"name":"Large language models for predicting one-year major adverse cardiovascular events in acute coronary syndrome.","description":"Effective risk stratification is crucial for managing acute coronary syndrome (ACS). This study evaluated whether general-purpose large language models (LLMs) can reliably execute the complex clinical reasoning required for cardiovascular prognosis. We quantitatively assessed three LLMs-ChatGPT 4o, DeepSeek R1, and Grok 3-for predicting one-year major adverse cardiovascular events (MACEs), using 29 guideline-recommended features from 903 participants in the LM-ACS cohort and 64 participants in the MIMIC database. All models demonstrated significant risk overestimation and substantial output variability across ten independent runs. Although Grok 3 showed the highest initial accuracy, its average performance over all runs showed no significant difference. ROC analysis indicated that none of ","dates":{"release":"2026-01-01T00:00:00Z","publication":"2026 Feb","modification":"2026-07-15T13:24:42.845Z","creation":"2026-07-05T03:08:23.549Z"},"accession":"S-EPMC12874424","cross_references":{"pubmed":["41660250"],"doi":["10.1016/j.isci.2026.114644"]}}