EHR Interaction Between Patients and AI: NoteAid EHR Interaction

TL;DR

This paper presents the NoteAid EHR Interaction Pipeline, leveraging generative LLMs to help patients understand their electronic health records through explanation and question-answering tasks, supported by new datasets and evaluations.

Contribution

It introduces a novel LLM-based pipeline for patient-EHR interaction, creating datasets and evaluation methods for EHR explanation and Q&A tasks from the patient's perspective.

Findings

LLMs effectively assist in patient education on EHR content.

New datasets with 10,000 and 876 instances support future research.

Manual evaluation confirms the potential of LLMs in this domain.

Abstract

With the rapid advancement of Large Language Models (LLMs) and their outstanding performance in semantic and contextual comprehension, the potential of LLMs in specialized domains warrants exploration. This paper introduces the NoteAid EHR Interaction Pipeline, an innovative approach developed using generative LLMs to assist in patient education, a task stemming from the need to aid patients in understanding Electronic Health Records (EHRs). Building upon the NoteAid work, we designed two novel tasks from the patient's perspective: providing explanations for EHR content that patients may not understand and answering questions posed by patients after reading their EHRs. We extracted datasets containing 10,000 instances from MIMIC Discharge Summaries and 876 instances from the MADE medical notes collection, respectively, executing the two tasks through the NoteAid EHR Interaction Pipeline with these data. Performance data of LLMs on these tasks were collected and constructed as the corresponding NoteAid EHR Interaction Dataset. Through a comprehensive evaluation of the entire dataset using LLM assessment and a rigorous manual evaluation of 64 instances, we showcase the potential of LLMs in patient education. Besides, the results provide valuable data support for future exploration and applications in this domain while also supplying high-quality synthetic datasets for in-house system training.