Hybrid Models in Digital Psychiatry: Toward Blended Human–AI Care

Read full text Summarise with VIRAT
Authors: Saeheon Jang
Cited by: 0
References: 58

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 disorders are a leading cause of global disability, yet many countries face shortages of mental-health professionals and limited access to timely, high-quality care.Advances in artificial intelligence (AI), including large language models, multimodal sensing, and digital phenotyping, offer potential solutions.However, concerns regarding safety, bias, privacy, and crisis management limit the use of AI as an autonomous clinical tool.This narrative review synthesizes evidence from 40 peer-reviewed studies, including randomized trials, behavioral sensing research, AIenabled clinical decision-support systems, and international regulatory frameworks.Across conversational agents, telepsychiatry augmentation, diagnostic algorithms, and large-scale implementations, AI improved scalability, enabled earlier detection of symptom changes, and supported personalized treatment when integrated within cliniciansupervised workflows.In contrast, fully autonomous systems showed risks such as hallucinated outputs, demographic bias, inconsistent crisis detection, and weak data governance.Hybrid digital psychiatry, combining AI with clinician oversight, appears to be the most clinically viable and ethically grounded approach.

Fields of Study & Subjects

Artificial Intelligence in Healthcare and Education Digital Mental Health Interventions Ethics and Social Impacts of AI

Publication details

Journal / source
Mood and Emotion
Volume
24
Issue
1
Pages
11–20
Publication date
31 March 2026
Language
EN