A Systematic Review of NLP for Dementia -- Tasks, Datasets and Opportunities

TL;DR

This systematic review analyzes over 240 NLP studies on dementia, highlighting current research areas, datasets, gaps, ethical issues, and opportunities for future advancements in the field.

Contribution

It provides a comprehensive overview of NLP applications in dementia, identifying key research areas, datasets, gaps, and ethical considerations to guide future work.

Findings

Half of the papers focus on dementia detection using clinical data.

Many unexplored directions include synthetic data and digital twins.

Diverse datasets are used, including recorded, written, and social media data.

Abstract

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.