Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models

TL;DR

This paper introduces a novel approach using large language models' perplexity scores to detect Alzheimer's dementia from language data, achieving higher accuracy and interpretability than existing methods.

Contribution

It extends paired perplexity detection to a recent LLM, improving accuracy and interpretability in Alzheimer's detection compared to prior methods.

Findings

3.33% accuracy improvement over current paired perplexity methods

6.35% accuracy improvement over ADReSS 2020 benchmark

LLMs learn language patterns specific to AD speakers

Abstract

Alzheimer's dementia (AD) is a neurodegenerative disorder with cognitive decline that commonly impacts language ability. This work extends the paired perplexity approach to detecting AD by using a recent large language model (LLM), the instruction-following version of Mistral-7B. We improve accuracy by an average of 3.33% over the best current paired perplexity method and by 6.35% over the top-ranked method from the ADReSS 2020 challenge benchmark. Our further analysis demonstrates that the proposed approach can effectively detect AD with a clear and interpretable decision boundary in contrast to other methods that suffer from opaque decision-making processes. Finally, by prompting the fine-tuned LLMs and comparing the model-generated responses to human responses, we illustrate that the LLMs have learned the special language patterns of AD speakers, which opens up possibilities for novel methods of model interpretation and data augmentation.