Explainable Identification of Dementia from Transcripts using Transformer Networks

Abstract

Alzheimer's disease (AD) is the main cause of dementia which is accompanied by loss of memory and may lead to severe consequences in peoples' everyday life if not diagnosed on time. Very few works have exploited transformer-based networks and despite the high accuracy achieved, little work has been done in terms of model interpretability. In addition, although Mini-Mental State Exam (MMSE) scores are inextricably linked with the identification of dementia, research works face the task of dementia identification and the task of the prediction of MMSE scores as two separate tasks. In order to address these limitations, we employ several transformer-based models, with BERT achieving the highest accuracy accounting for 87.50%. Concurrently, we propose an interpretable method to detect AD patients based on siamese networks reaching accuracy up to 83.75%. Next, we introduce two multi-task learning models, where the main task refers to the identification of dementia (binary classification), while the auxiliary one corresponds to the identification of the severity of dementia (multiclass classification). Our model obtains accuracy equal to 86.25% on the detection of AD patients in the multi-task learning setting. Finally, we present some new methods to identify the linguistic patterns used by AD patients and non-AD ones, including text statistics, vocabulary uniqueness, word usage, correlations via a detailed linguistic analysis, and explainability techniques (LIME). Findings indicate significant differences in language between AD and non-AD patients.

IEEE Journal of Biomedical and Health Informatics (Accepted)

References in corpus (3)

• Publicly Available Clinical BERT Embeddings
• ConvBERT: Improving BERT with Span-based Dynamic Convolution
• Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer's Dementia recognition from spontaneous speech

Cited by in corpus (9)

• Calibration of Transformer-based Models for Identifying Stress and Depression in Social Media
• Depression detection in social media posts using transformer-based models and auxiliary features
• Detecting Dementia from Speech and Transcripts using Transformers
• Context-aware attention layers coupled with optimal transport domain adaptation and multimodal fusion methods for recognizing dementia from spontaneous speech
• Multitask learning for recognizing stress and depression in social media
• CogniAlign: Word-Level Multimodal Speech Alignment with Gated Cross-Attention for Alzheimer's Detection
• Improving Transformer Performance for French Clinical Notes Classification Using Mixture of Experts on a Limited Dataset
• LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data
• Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques