LLM-MINE: Large Language Model based Alzheimer's Disease and Related Dementias Phenotypes Mining from Clinical Notes

TL;DR

This paper introduces LLM-MINE, a framework utilizing large language models to automatically extract Alzheimer's and dementia-related phenotypes from unstructured clinical notes, improving disease staging and cohort analysis.

Contribution

The paper presents a novel LLM-based approach for extracting ADRD phenotypes from clinical notes, outperforming traditional methods like NER and dictionary-based baselines.

Findings

Chi-square confirms significant phenotype differences across cohorts.

Few-shot prompting yields the best clustering performance (ARI=0.290, NMI=0.232).

LLM-MINE effectively discovers meaningful ADRD signals from unstructured notes.

Abstract

Accurate extraction of Alzheimer's Disease and Related Dementias (ADRD) phenotypes from electronic health records (EHR) is critical for early-stage detection and disease staging. However, this information is usually embedded in unstructured textual data rather than tabular data, making it difficult to be extracted accurately. We therefore propose LLM-MINE, a Large Language Model-based phenotype mining framework for automatic extraction of ADRD phenotypes from clinical notes. Using two expert-defined phenotype lists, we evaluate the extracted phenotypes by examining their statistical significance across cohorts and their utility for unsupervised disease staging. Chi-square analyses confirm statistically significant phenotype differences across cohorts, with memory impairment being the strongest discriminator. Few-shot prompting with the combined phenotype lists achieves the best clustering performance (ARI=0.290, NMI=0.232), substantially outperforming biomedical NER and dictionary-based baselines. Our results demonstrate that LLM-based phenotype extraction is a promising tool for discovering clinically meaningful ADRD signals from unstructured notes.