Artificial Intelligence for Mental Health and Mental Illnesses: An Overview

Purpose of review: Artificial intelligence (AI) holds promise to transform mental healthcare but also presents pitfalls. This article provides an overview of AI and current applications in healthcare, a review of recent original research on AI specific to mental health, and a discussion of how AI can supplement clinical practice while considering its current limitations, areas needing additional research, and ethical implications. Recent findings: The authors reviewed 28 studies using electronic health records (EHRs), mood rating scales, brain imaging, novel monitoring systems (e.g., smartphone, video), and social media to predict, classify, or subgroup mental health conditions including depression, schizophrenia/other psychiatric illnesses, and suicide ideation/attempts. Collectively, these studies revealed high accuracies and provide examples of AI’s potential in mental healthcare, but most are early proof-of-concept works demonstrating feasibility and comparative algorithm performance. Summary: As AI techniques are refined, it may be possible to define mental illnesses more objectively than DSM-5, identify illnesses earlier or in prodromal stages when interventions may be more effective, and personalize treatments. However, caution is necessary to avoid over-interpreting preliminary results, and more work is required to bridge AI research and clinical care.