Leveraging Prompt Learning and Pause Encoding for Alzheimer's Disease Detection

TL;DR

This study enhances Alzheimer's disease detection from speech transcripts by applying prompt learning, incorporating pause information, and using ensemble methods, achieving state-of-the-art accuracy with manual transcripts.

Contribution

It introduces prompt-based fine-tuning of pre-trained language models and explores pause encoding, improving AD detection accuracy over traditional methods.

Findings

Maximum detection accuracy of 95.8% with manual transcripts

Prompt-based fine-tuning outperforms traditional fine-tuning

Ensemble techniques improve robustness and accuracy

Abstract

Compared to other clinical screening techniques, speech-and-language-based automated Alzheimer's disease (AD) detection methods are characterized by their non-invasiveness, cost-effectiveness, and convenience. Previous studies have demonstrated the efficacy of fine-tuning pre-trained language models (PLMs) for AD detection. However, the objective of this traditional fine-tuning method, which involves inputting only transcripts, is inconsistent with the masked language modeling (MLM) task used during the pre-training phase of PLMs. In this paper, we investigate prompt-based fine-tuning of PLMs, converting the classification task into a MLM task by inserting prompt templates into the transcript inputs. We also explore the impact of incorporating pause information from forced alignment into manual transcripts. Additionally, we compare the performance of various automatic speech recognition (ASR) models and select the Whisper model to generate ASR-based transcripts for comparison with manual transcripts. Furthermore, majority voting and ensemble techniques are applied across different PLMs (BERT and RoBERTa) using different random seeds. Ultimately, we obtain maximum detection accuracy of 95.8% (with mean 87.9%, std 3.3%) using manual transcripts, achieving state-of-the-art performance for AD detection using only transcripts on the ADReSS test set.