A Systematic Review of NLP for Dementia -- Tasks, Datasets and Opportunities
This review provides a comprehensive overview of the current state and future opportunities for NLP researchers and medical professionals working on dementia, identifying gaps in research and ethical considerations.
This systematic review analyzed over 240 papers on NLP for dementia, identifying key research areas such as dementia detection, linguistic biomarker extraction, caregiver support, and patient assistance. It found that 50% of the papers focused exclusively on dementia detection using clinical data, while highlighting unexplored directions and ethical dilemmas.
The close link between cognitive decline and language has fostered long-standing collaboration between the NLP and medical communities in dementia research. To examine this, we reviewed over 240 papers applying NLP to dementia-related efforts, drawing from medical, technological, and NLP-focused literature. We identify key research areas, including dementia detection, linguistic biomarker extraction, caregiver support, and patient assistance, showing that half of all papers focus solely on dementia detection using clinical data. Yet, many directions remain unexplored -- artificially degraded language models, synthetic data, digital twins, and more. We highlight gaps and opportunities around trust, scientific rigor, applicability and cross-community collaboration. We raise ethical dilemmas in the field, and highlight the diverse datasets encountered throughout our review -- recorded, written, structured, spontaneous, synthetic, clinical, social media-based, and more. This review aims to inspire more creative, impactful, and rigorous research on NLP for dementia.