Early Prediction of Multiple Major Adverse Cardiovascular Events in Acute Coronary Syndrome: Comparison of Feature-Extraction Pipelines and Fine-Tuned Large Language Models

Large language models (LLMs) have shown promise for supporting clinical decision-making from unstructured health records. This study provides a systematic comparison of feature-extraction pipelines and end-to-end fine-tuned LLMs for the early prediction of major adverse cardiovascular events (MACE) using the earliest available clinical notes from patients with acute coronary syndrome (ACS). Clinical notes from 2,650 patients with ST-elevation myocardial infarction (STEMI) and non-ST-elevation myocardial infarction (NSTEMI) were extracted from the MIMIC-III database. Feature-extraction approaches based on TF-IDF, word embeddings, and transformer representations combined with machine learning classifiers were compared against end-to-end fine-tuned LLMs in a multilabel prediction setting. Fine-tuned LLMs consistently outperformed feature-extraction pipelines. The best-performing model achieved AUC improvements of 18.2%, 17.3%, 9.1%, 12.4%, and 15.3% in STEMI, and 17.2%, 7.5%, 9.2%, 14.5%, and 10.0% in NSTEMI for predicting in-hospital mortality, reinfarction, heart failure, cardiogenic shock, and MACE, respectively. These findings suggest that fine-tuned LLMs can effectively leverage admission clinical narratives for early cardiovascular risk stratification and identification of high-risk patients.