Views of People With Psychosis About Algorithm-Based Relapse Prediction and Data Sharing: Qualitative Study
Journal of Medical Internet Research · 2026
DOI: 10.2196/86753 ↗Kurz gefasst
Qualitative Studie in der Zeitschrift Journal of Medical Internet Research, 2026. Verfasst von Emily Eisner und 22 weiteren Autor:innen. Beteiligte Einrichtung: Division of Psychology and Mental Health, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Jean McFarlan…. Hauptthemen laut MEDLINE: Psychotic Disorders, Algorithms, Information Dissemination. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Preventing relapses of psychosis is difficult and important. Digital remote monitoring (DRM) systems are being developed and tested to support this. Increasingly, these systems use algorithm-based relapse prediction. Hence, understanding stakeholder views about algorithmic prediction is crucial. Existing qualitative work has explored health professionals’ views, but very few studies have examined the perspectives of people with psychosis on this topic.
Objective
This paper aimed to provide an in-depth examination of the views of people with psychosis regarding algorithmic relapse prediction within a DRM system that incorporates active symptom monitoring and passive sensing data.
Methods
People with psychosis (n=58) were recruited from 6 geographically distinct areas of the United Kingdom. They participated in semistructured qualitative interviews exploring their views about using a DRM system that predicts psychosis relapse based on a machine learning algorithm. Transcripts were analyzed using reflexive thematic analysis. People with lived experience of psychosis were involved extensively in study design, analysis, and reporting.
Results
Findings were described across 4 themes. First, accuracy was a prominent theme. Participants emphasized that transparency about algorithm sensitivity and specificity is crucial and discussed the risks of the relapse prediction algorithm producing false positives (flagging that someone was relapsing when they were not) and false negatives (missing actual relapses). In both cases, participants said that errors may be partially mitigated through a human-in-the-loop approach (theme 2), with DRM blended with human oversight, from clinicians or a dedicated digital monitoring team, and calibrated based on service user, carer, and clinician feedback. The third theme, trust, fears, and choice, noted the interplay between users’ trust in the DRM system and their relationship with the clinical team. This theme described participants’ fears about potential overreactions (hospitalization or excessive medication) or underreactions (no additional support) from the clinical team in response to algorithm-generated relapse predictions. It emphasized the importance of retaining choice around the use of relapse detection algorithms and the sharing of personal data. The final theme described participants’ views about the benefits of using a relapse prediction algorithm , including facilitating early intervention, triaging care according to need, minimizing human bias in assessment, and efficiency in saving staff time.
Conclusions
People with psychosis acknowledged potential benefits of algorithm-assisted relapse prediction for receiving timely or efficient care, but with several caveats. Algorithm-generated relapse alerts need to be sufficiently accurate and must be interpreted, with understanding of their limitations, by a trustworthy human who is aware of the relevant context. Algorithm-based relapse predictions should only be used with valid consent, in a way that promotes and respects the autonomy and voice of service users and avoids increasing the use of excessive restriction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Psychology and Mental Health, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Jean McFarlane Building, Manchester, United Kingdom, +44 1613066000.
- Greater Manchester Mental Health NHS Foundation Trust, Manchester, United Kingdom.
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, United Kingdom.
- Department of Psychology, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, United Kingdom.
- South London and Maudsley NHS Foundation Trust, London, United Kingdom.
- McPin Foundation, London, United Kingdom.
Zitieren
APA
Eisner, E., Ball, H., Ainsworth, J., Cella, M., Drake, R. J., Elton, D., Faulkner, S., Greenwood, K., Gumley, A., Haddock, G., Kendall, K. M., Kenny, A., Krogsæter, T. I., Lees, J., Lewis, S., Phiri, A., Schwannauer, M., Turner, R., Walsh, A. E. L., …, & Bucci, S. (2026). Views of People With Psychosis About Algorithm-Based Relapse Prediction and Data Sharing: Qualitative Study. Journal of Medical Internet Research. https://doi.org/10.2196/86753
Vancouver
Eisner E, Ball H, Ainsworth J, Cella M, Drake RJ, Elton D, et al. Views of People With Psychosis About Algorithm-Based Relapse Prediction and Data Sharing: Qualitative Study. Journal of Medical Internet Research. 2026. doi:10.2196/86753
BibTeX
@article{Eisner2026,
author = {Eisner, Emily and Ball, Hannah and Ainsworth, John and Cella, Matteo and Drake, Richard J and Elton, Daniel and Faulkner, Sophie and Greenwood, Kathryn and Gumley, Andrew and Haddock, Gillian and Kendall, Kimberley M and Kenny, Alex and Krogsæter, Tor-Ivar and Lees, Jane and Lewis, Shôn and Phiri, Alie and Schwannauer, Matthias and Turner, Rebecca and Walsh, Annabel E L and Walters, James and Wykes, Til and Zahid, Uzma and Bucci, Sandra},
title = {Views of People With Psychosis About Algorithm-Based Relapse Prediction and Data Sharing: Qualitative Study},
journal = {Journal of Medical Internet Research},
year = {2026},
doi = {10.2196/86753}
}
EUVIMED