Semantic Coherence Markers for the Early Diagnosis of the Alzheimer Disease

TL;DR

This study demonstrates that language model perplexity scores can accurately distinguish between healthy individuals and those with Alzheimer’s disease, offering a promising tool for early diagnosis based on language analysis.

Contribution

The paper introduces the use of perplexity scores from various language models as a novel method for early Alzheimer’s detection through language transcript analysis.

Findings

Perplexity scores achieved 100% accuracy in classification.

Transformer-based GPT-2 outperformed n-gram models.

Language models can effectively discriminate between healthy and Alzheimer’s-affected speech.

Abstract

In this work we explore how language models can be employed to analyze language and discriminate between mentally impaired and healthy subjects through the perplexity metric. Perplexity was originally conceived as an information-theoretic measure to assess how much a given language model is suited to predict a text sequence or, equivalently, how much a word sequence fits into a specific language model. We carried out an extensive experimentation with the publicly available data, and employed language models as diverse as N-grams, from 2-grams to 5-grams, and GPT-2, a transformer-based language model. We investigated whether perplexity scores may be used to discriminate between the transcripts of healthy subjects and subjects suffering from Alzheimer Disease (AD). Our best performing models achieved full accuracy and F-score (1.00 in both precision/specificity and recall/sensitivity) in categorizing subjects from both the AD class and control subjects. These results suggest that perplexity can be a valuable analytical metrics with potential application to supporting early diagnosis of symptoms of mental disorders.