Evaluating GPT's Capability in Identifying Stages of Cognitive Impairment from Electronic Health Data

TL;DR

This study evaluates GPT-4o's ability to identify and stage cognitive impairment from electronic health records, demonstrating high accuracy and potential for clinical and research applications.

Contribution

The paper introduces an automated, zero-shot GPT-4o approach for staging cognitive impairment from EHRs, showing promising accuracy in clinical and research contexts.

Findings

GPT-4o achieved a weighted kappa of 0.83 for CDR staging.

GPT-4o attained a weighted kappa of 0.91 for differentiating cognition levels.

High confidence cases reached a weighted kappa of 0.96.

Abstract

Identifying cognitive impairment within electronic health records (EHRs) is crucial not only for timely diagnoses but also for facilitating research. Information about cognitive impairment often exists within unstructured clinician notes in EHRs, but manual chart reviews are both time-consuming and error-prone. To address this issue, our study evaluates an automated approach using zero-shot GPT-4o to determine stage of cognitive impairment in two different tasks. First, we evaluated the ability of GPT-4o to determine the global Clinical Dementia Rating (CDR) on specialist notes from 769 patients who visited the memory clinic at Massachusetts General Hospital (MGH), and achieved a weighted kappa score of 0.83. Second, we assessed GPT-4o's ability to differentiate between normal cognition, mild cognitive impairment (MCI), and dementia on all notes in a 3-year window from 860 Medicare patients. GPT-4o attained a weighted kappa score of 0.91 in comparison to specialist chart reviews and 0.96 on cases that the clinical adjudicators rated with high confidence. Our findings demonstrate GPT-4o's potential as a scalable chart review tool for creating research datasets and assisting diagnosis in clinical settings in the future.