LLM-Augmented Symptom Analysis for Cardiovascular Disease Risk Prediction: A Clinical NLP

TL;DR

This paper presents a novel NLP pipeline using domain-adapted large language models to extract symptoms from clinical notes, improving cardiovascular risk prediction accuracy and clinical relevance.

Contribution

It introduces an LLM-augmented clinical NLP approach with cardiovascular-specific fine-tuning and prompt-based reasoning, addressing challenges like hallucination and temporal ambiguity.

Findings

Enhanced prediction performance on MIMIC-III and CARDIO-NLP datasets.

High clinical relevance with kappa = 0.82.

Addresses key challenges in LLM clinical applications.

Abstract

Timely identification and accurate risk stratification of cardiovascular disease (CVD) remain essential for reducing global mortality. While existing prediction models primarily leverage structured data, unstructured clinical notes contain valuable early indicators. This study introduces a novel LLM-augmented clinical NLP pipeline that employs domain-adapted large language models for symptom extraction, contextual reasoning, and correlation from free-text reports. Our approach integrates cardiovascular-specific fine-tuning, prompt-based inference, and entity-aware reasoning. Evaluations on MIMIC-III and CARDIO-NLP datasets demonstrate improved performance in precision, recall, F1-score, and AUROC, with high clinical relevance (kappa = 0.82) assessed by cardiologists. Challenges such as contextual hallucination, which occurs when plausible information contracts with provided source, and temporal ambiguity, which is related with models struggling with chronological ordering of events are addressed using prompt engineering and hybrid rule-based verification. This work underscores the potential of LLMs in clinical decision support systems (CDSS), advancing early warning systems and enhancing the translation of patient narratives into actionable risk assessments.