Previously submitted to: JMIR Mental Health (no longer under consideration since Jan 07, 2026)
Date Submitted: Jan 6, 2026
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Using Artificial Intelligence to Detect Relapse of Psychosis: A Scoping Review
ABSTRACT
Background:
Psychotic disorder represents a leading cause of disability worldwide, and relapse in psychosis is common. Artificial intelligence (AI) is increasingly recognized as a method which could aid clinical monitoring in psychosis. This scoping review aims to identify studies which have used methods with an AI component to detect relapse in psychosis.
Objective:
Our primary research aim in this study is to map the literature in this area to determine which AI tools have been studied to detect psychosis relapse. A secondary aim is to provide a narrative synthesis of the efficacy reported in each study.
Methods:
A systematic search strategy was conducted on PubMed, PsycINFO and Embase from inception to July 2025. Observational studies, randomized controlled trials and quasi-experimental studies which used AI methods to detect relapse in psychosis were eligible for inclusion. Screening and data extraction procedures were conducted by at least two reviewers working independently. Findings were extracted, charted and described using narrative synthesis based on data extraction and consensus meetings with the research team. The scoping review was prospectively registered with Open Science Framework
Results:
Relevant studies identified (n = 9) included use of digital tools such as smartphone and smartwatch-based monitoring, ecological momentary assessment tools, social media activity and internet searches. Digital phenotyping via smartphones and wearables emerged as the most common method for data collection. Efficacy of AI models varied with sensitivity (or recall) ranging from 0.25 to 0.77 and specificity (or precision) ranging from 0.06 to 0.88. Reported area under the receiver operating characteristic curve for models ranged from 0.63 to 0.78. AI models were heterogenous across studies, and most study findings were not replicated.
Conclusions:
This scoping review highlights both the promise and current limitations of AI in psychosis relapse prediction. Digital phenotyping research in detection of psychosis relapse has progressed, but future studies need to include larger numbers of participants and should incorporate other methods such as use of large language models. Future studies will require large collaborations aiming to deliver AI tools for use in real world clinical practice. Clinical Trial: N/A
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.