Early Detection of Mental Health Disorders using Explainable AI and Digital Behavioral Signals

Read full text Summarise with VIRAT
Authors: Gaurav Borthakur
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Mental health disorders such as depression and anxiety are major global health concerns, yet many cases remain undetected in their early stages. With the widespread use of smartphones and digital platforms, individuals generate continuous behavioural data through daily activities such as communication, mobility, and online interactions. These digital behavioural signals can provide valuable insights into changes in mental well-being. This study explores the use of explainable artificial intelligence (XAI) to analyse digital behavioural data for the early detection of mental health risks. Data derived from smartphone usage patterns, activity levels, and textual content from online platforms can be examined using machine learning techniques to identify behavioural changes associated with psychological distress. Explainable AI methods are incorporated to ensure that the reasons behind model predictions are transparent and understandable. The research also emphasizes ethical considerations including user privacy, informed consent, and fairness in algorithmic analysis. Overall, this approach highlights the potential of combining digital behavioural signals with explainable AI to support early mental health screening while maintaining responsible and ethical use of technology.

Fields of Study & Subjects

Mental Health via Writing Emotion and Mood Recognition Digital Mental Health Interventions

Publication details

Journal / source
International Journal for Research in Applied Science and Engineering Technology
Volume
14
Issue
3
Pages
3153–3158
Publication date
25 March 2026
Language
EN