Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges

Anonymous

TL;DR: We propose and evaluate an approach using LLMs to extract evidence from EHR notes to aid diagnosis.

Abstract:

Unstructured data in Electronic Health Records (EHRs) often contains critical information---complementary to imaging---that could inform radiologists' diagnoses. But the large volume of notes often associated with patients together with time constraints renders manually identifying relevant evidence practically infeasible. In this work we propose and evaluate a zero-shot strategy for using LLMs as a mechanism to efficiently retrieve and summarize unstructured evidence in patient EHR relevant to a given query. Our method entails tasking an LLM to infer whether a patient has, or is at risk of, a particular condition on the basis of associated notes; if so, we ask the model to summarize the supporting evidence. Under expert evaluation (radiologist) manual and automated evaluations, we find that this LLM-based approach provides outputs consistently preferred to a pre-LLM information retrieval baseline.
Manual evaluation is expensive, so we also propose and validate a method using an LLM to evaluate (other) LLM outputs for this task, allowing us to scale up our own evaluation. Our findings indicate the promise of LLMs as interfaces to EHR, but also highlight the key outstanding challenge: "hallucinations". In this setting, however, we show that model confidence in outputs strongly correlates with faithful summaries, offering a practical means to limit confabulations.

Paper Type: long

Research Area: NLP Applications

Contribution Types: NLP engineering experiment, Approaches to low-resource settings

Languages Studied: English