Linguistic Features Extracted by GPT-4 Improve Alzheimer's Disease Detection based on Spontaneous Speech

TL;DR

This study uses GPT-4 to extract semantic speech features that improve early Alzheimer's detection from spontaneous speech, demonstrating the potential of large language models in clinical linguistic analysis.

Contribution

It introduces a novel method leveraging GPT-4 for extracting semantic features that enhance Alzheimer's detection accuracy from speech transcripts.

Findings

GPT-4 features improve AD detection accuracy

Features validated against human raters and proxies

Effective on both manual and automatic transcripts

Abstract

Alzheimer's Disease (AD) is a significant and growing public health concern. Investigating alterations in speech and language patterns offers a promising path towards cost-effective and non-invasive early detection of AD on a large scale. Large language models (LLMs), such as GPT, have enabled powerful new possibilities for semantic text analysis. In this study, we leverage GPT-4 to extract five semantic features from transcripts of spontaneous patient speech. The features capture known symptoms of AD, but they are difficult to quantify effectively using traditional methods of computational linguistics. We demonstrate the clinical significance of these features and further validate one of them ("Word-Finding Difficulties") against a proxy measure and human raters. When combined with established linguistic features and a Random Forest classifier, the GPT-derived features significantly improve the detection of AD. Our approach proves effective for both manually transcribed and automatically generated transcripts, representing a novel and impactful use of recent advancements in LLMs for AD speech analysis.