JMIR Publications

ABSTRACT

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 aims 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 six geographically distinct areas of the UK. They participated in 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 are described across four themes: 1. Accuracy. Participants raised concerns about risks of false positives (flagging relapse when well) and false negatives (missing actual relapses) and emphasized that transparency about algorithm sensitivity/specificity is crucial. 2. Human-in-the-loop. Errors may be partially mitigated by blending DRM with human oversight from clinicians or a dedicated digital monitoring team, and by calibrating the system based on service user, carer, and clinician feedback. 3. Trust, fears and choice. Users’ trust in DRM was related to their relationship with the clinical team. Without trust, participants feared that clinicians would over- or underreact to DRM relapse alerts. Having choices about using DRM and about sharing alerts is essential. 4. Benefits of a relapse prediction algorithm. Participants described benefits of sharing DRM alerts: 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 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 services users and avoids increasing the use of excessive restriction.