Automatic Depression Assessment using Machine Learning: A Comprehensive Survey

TL;DR

This survey comprehensively reviews machine learning-based approaches for automatic depression assessment across multiple human behaviour modalities, highlighting current methods, datasets, challenges, and future research directions.

Contribution

It provides the first extensive review of multi-modal human behaviours for ML-based depression assessment, filling a gap in existing literature.

Findings

Summarizes depression-related human behaviours across multiple modalities.

Reviews and compares ML-based ADA approaches, datasets, and challenges.

Identifies key opportunities for future research in multi-modal depression assessment.

Abstract

Depression is a common mental illness across current human society. Traditional depression assessment relying on inventories and interviews with psychologists frequently suffer from subjective diagnosis results, slow and expensive diagnosis process as well as lack of human resources. Since there is a solid evidence that depression is reflected by various human internal brain activities and external expressive behaviours, early traditional machine learning (ML) and advanced deep learning (DL) models have been widely explored for human behaviour-based automatic depression assessment (ADA) since 2012. However, recent ADA surveys typically only focus on a limited number of human behaviour modalities. Despite being used as a theoretical basis for developing ADA approaches, existing ADA surveys lack a comprehensive review and summary of multi-modal depression-related human behaviours. To bridge this gap, this paper specifically summarises depression-related human behaviours across a range of modalities (e.g. the human brain, verbal language and non-verbal audio/facial/body behaviours). We focus on conducting an up-to-date and comprehensive survey of ML-based ADA approaches for learning depression cues from these behaviours as well as discussing and comparing their distinctive features and limitations. In addition, we also review existing ADA competitions and datasets, identify and discuss the main challenges and opportunities to provide further research directions for future ADA researchers.