EUVIMEDAtrasti EUVIMED
Scoping ReviewOpen access

Using AI to Detect Psychosis Relapse: Scoping Review

Lorenzo Ghelfi, Jack Healy, Francesco Piacenza, Ian French, Nicholas McNamara, Khyber Afridi Rabbi, Benjamin Bond, Emma O'Hora, Darren Roddy, Moyyad Kamali, Sudipto Das, Sandra Anna Just and 15 more

JMIR Mental Health · 2026

DOI: 10.2196/92192 ↗

At a glance

Scoping Review in JMIR Mental Health, 2026. Written by Lorenzo Ghelfi and 26 co-authors. Institution: Department of Psychiatry, Royal College of Surgeons in Ireland, Smurfit Building, Beaumont, Dublin, Co Dublin, D09 YD60, Ireland, 353 0832026617. Major MEDLINE topics: Psychotic Disorders, Artificial Intelligence. Cited 1 times so far (Crossref); 63 references. The full text is freely available in PubMed Central.

SantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

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 that could aid clinical monitoring for individuals experiencing psychosis.

Objective

This review aims to map the existing literature on AI-based approaches—including machine learning, deep learning, and natural language processing—used to detect relapse in individuals with psychotic disorders.

Methods

A systematic search strategy was conducted on PubMed, PsycINFO, and Embase up to January 7, 2026. Observational studies, randomized controlled trials, and quasi-experimental studies that used AI methods to detect relapse in psychosis were eligible for inclusion. Screening and data extraction procedures were conducted by at least 2 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 the Open Science Framework.

Results

Relevant studies identified (N=10) included the 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. The 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. The reported area under the receiver operating characteristic curve for models ranged from 0.63 to 0.78. AI models were heterogeneous across studies, and most study findings were not replicated.

Conclusions

This scoping review highlights both the promise and the current limitations of AI in psychosis relapse detection. Passive digital phenotyping research in the detection of psychosis relapse has progressed, and personalized approaches with individual-level modeling show promise; however, further studies need to include larger numbers of participants and should incorporate methods such as large language models. Future studies will require large collaborations aimed at delivering AI methods for use in real-world clinical practice.

Subjects

MeSH terms (MEDLINE)

Psychotic DisordersArtificial IntelligenceHumansRecurrenceMachine LearningDeep Learning

Author keywords

AIartificial intelligencedeep learningdigital phenotypingmachine learningpsychosisrelapseschizophreniascoping review

Authors and institutions

  • Department of Psychiatry, Royal College of Surgeons in Ireland, Smurfit Building, Beaumont, Dublin, Co Dublin, D09 YD60, Ireland, 353 0832026617.
  • University Hospital Waterford, Waterford, Munster, Ireland.
  • Health Service Executive, Leinster, Ireland.
  • Trinity College Dublin, Dublin, Leinster, Ireland.
  • Ennis Hospital, Ennis, Ireland.
  • FutureNeuro Research Centre, RCSI University of Medicine and Health Sciences, Dublin, Co Dublin, Ireland.

Cite

APA

Ghelfi, L., Healy, J., Piacenza, F., French, I., McNamara, N., Rabbi, K. A., Bond, B., O'Hora, E., Roddy, D., Kamali, M., Das, S., Just, S. A., Tedeschi, E., Hussain, M., Mikalsen, K. Ø., Kaiser, S., Cecere, G., Koops, S., de Boer, J., …, & Lyne, J. P. (2026). Using AI to Detect Psychosis Relapse: Scoping Review. JMIR Mental Health. https://doi.org/10.2196/92192

Vancouver

Ghelfi L, Healy J, Piacenza F, French I, McNamara N, Rabbi KA, et al. Using AI to Detect Psychosis Relapse: Scoping Review. JMIR Mental Health. 2026. doi:10.2196/92192

BibTeX
@article{Ghelfi2026,
  author = {Ghelfi, Lorenzo and Healy, Jack and Piacenza, Francesco and French, Ian and McNamara, Nicholas and Rabbi, Khyber Afridi and Bond, Benjamin and O'Hora, Emma and Roddy, Darren and Kamali, Moyyad and Das, Sudipto and Just, Sandra Anna and Tedeschi, Enrico and Hussain, Musarrat and Mikalsen, Karl Øyvind and Kaiser, Stefan and Cecere, Giacomo and Koops, Sanne and de Boer, Janna and Nguyen, Elysie and Bora, Emre and Hinzen, Wolfram and Homan, Philipp and Sommer, Iris E and Cotter, David and Cannon, Mary and Lyne, John Paul},
  title = {Using AI to Detect Psychosis Relapse: Scoping Review},
  journal = {JMIR Mental Health},
  year = {2026},
  doi = {10.2196/92192}
}
Start for free →