Mining Social Determinants of Health for Heart Failure Patient 30-Day Readmission via Large Language Model

TL;DR

This paper uses large language models to extract social determinants of health from clinical notes and analyzes their impact on 30-day readmission risk for heart failure patients, providing insights to improve patient outcomes.

Contribution

It introduces a novel application of LLMs for extracting SDOHs from unstructured clinical text and links these factors to readmission risk, which was previously underexplored.

Findings

Identified key SDOHs associated with readmission, such as tobacco use and transportation issues.

Demonstrated the effectiveness of LLMs in extracting relevant social factors from clinical notes.

Provided actionable insights for healthcare providers to reduce readmission rates.

Abstract

Heart Failure (HF) affects millions of Americans and leads to high readmission rates, posing significant healthcare challenges. While Social Determinants of Health (SDOH) such as socioeconomic status and housing stability play critical roles in health outcomes, they are often underrepresented in structured EHRs and hidden in unstructured clinical notes. This study leverages advanced large language models (LLMs) to extract SDOHs from clinical text and uses logistic regression to analyze their association with HF readmissions. By identifying key SDOHs (e.g. tobacco usage, limited transportation) linked to readmission risk, this work also offers actionable insights for reducing readmissions and improving patient care.