Leveraging Prompt Learning and Pause Encoding for Alzheimer's Disease Detection
For researchers in automated Alzheimer's detection, this work provides a new SOTA on a standard benchmark using a prompt learning approach, though it is an incremental application of existing methods.
This paper applies prompt-based fine-tuning of pre-trained language models (PLMs) to Alzheimer's disease detection from speech transcripts, achieving state-of-the-art accuracy of 95.8% (mean 87.9%) on the ADReSS test set, outperforming prior transcript-only methods.
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.