Structured Semantics from Unstructured Notes: Language Model Approaches to EHR-Based Decision Support

TL;DR

This paper investigates how large language models can extract meaningful semantic information from unstructured EHR notes and codes to enhance clinical decision support, addressing challenges of data harmonization, fairness, and generalizability.

Contribution

It introduces novel language model techniques for extracting structured semantics from unstructured EHR data to improve decision support systems.

Findings

Text features provide rich semantic representations.

Language models help harmonize data across institutions.

Challenges include ensuring model fairness and generalizability.

Abstract

The advent of large language models (LLMs) has opened new avenues for analyzing complex, unstructured data, particularly within the medical domain. Electronic Health Records (EHRs) contain a wealth of information in various formats, including free text clinical notes, structured lab results, and diagnostic codes. This paper explores the application of advanced language models to leverage these diverse data sources for improved clinical decision support. We will discuss how text-based features, often overlooked in traditional high dimensional EHR analysis, can provide semantically rich representations and aid in harmonizing data across different institutions. Furthermore, we delve into the challenges and opportunities of incorporating medical codes and ensuring the generalizability and fairness of AI models in healthcare.