AI in Psychiatry for Improving Continuity of Patient Care: Protocol for a Mixed Methods Systematic Review

Area of Science:

• Psychiatric care
• Artificial Intelligence (AI)
• Machine Learning (ML)

Background:

• Continuity of care is crucial in mental health due to chronic conditions, but care pathways are fragmented.
• AI and ML offer potential for tracking data and automating decisions, yet their efficacy in psychiatric care continuity is unassessed.
• This systematic review protocol addresses the need for evaluating AI-driven workflows in enhancing psychiatric care coordination.

Purpose of the Study:

• To evaluate the effectiveness of AI and ML interventions in improving continuity of patient care within psychiatric settings.
• To stratify different AI architectures used in mental health.
• To identify barriers and facilitators for implementing AI in psychiatric care.

Main Methods:

• A systematic literature search across major databases (MEDLINE, Embase, CENTRAL, CINAHL, APA PsycInfo) for studies from 2016-2025.
• Inclusion of randomized controlled trials, non-randomized interventional studies, and qualitative/mixed methods evaluations.
• Mixed methods convergent synthesis using the Joanna Briggs Institute (JBI) approach for quantitative and qualitative data.

Main Results:

• The systematic review is registered with PROSPERO (CRD420251245352) and self-funded.
• Database searches have commenced, with full-text screening and data analysis projected for completion by early spring 2027.
• This review will synthesize evidence on AI/ML effectiveness and implementation factors in psychiatric care.

Conclusions:

• The review will clarify the clinical effectiveness, ethical considerations, and implementation factors of AI tools in psychiatry.
• Consolidated insights will inform clinical guidelines and governance frameworks for mental health systems.
• The findings aim to support the design of proactive, learning mental health systems utilizing AI.