Leveraging Large Language Models with Sequential Prompting to Extract Eye Examination Findings from Free-Text Ophthalmology Notes.

ABSTRACT:

Purpose

The purpose of this study was to evaluate the ability of general domain large language models (LLMs) to identify slit lamp and fundus examination (FE) findings from free-text clinical notes in electronic health records.

Design

Retrospective cohort study.

Participants

Data were obtained from the Stanford Research Repository, which contains progress notes of patients from the Department of Ophthalmology at Stanford University since 2008.

Methods

We assessed a local LLM pipeline, using a novel sequential named entity recognition (NER) prompting approach, for identifying eye examination findings and their lateralities from free-text clinical notes at a single academic center. We compared several local open-source LLMs, including Mistral Nemo 12B, Llama 3.1

SUBMITTER: Ruan FY 

PROVIDER: S-EPMC12615718 | biostudies-literature | 2026 Jan

REPOSITORIES: biostudies-literature