Pilot Study of Sensor-Informed Smartphone-based Mental Health Interventions for Mood in Early Psychosis

Negative mood symptoms are highly prevalent in early psychosis and strongly linked to long-term functional impairment and risk of relapse. Smartphone-based interventions offer a scalable and accessible solution for delivering personalized mental health support in daily life.

The goal of this micro randomized trial (MRT) is to evaluate the feasibility of using passive smartphone sensor data and machine learning to identify optimal moments for delivering smartphone app-based brief mental health interventions such as mindfulness exercises and psychoeducation, specifically moments when individuals are both most in need of support and most receptive to it.

The primary aim of this pilot study is to assess the feasibility and acceptability of the MRT study design, including recruitment and retention rates, EMA adherence, and participant feedback gathered through qualitative exit interviews to inform future design improvements. A secondary aim is to evaluate the feasibility of training an idiographic machine learning model using passive smartphone sensor data to detect moments of heightened negative affect. An exploratory aim is to estimate preliminary intervention effect sizes to inform a future fully powered clinical trial and to identify contextual factors associated with participant engagement.

• Smartphone-based Mindfulness Exercise (Behavioral): A brief approximately 1 minute video guided mindfulness based breathing exercise designed to anchor attention to the present moment and reduce negative affect in the moment by guiding participants through a structured breathing technique.
• Smartphone-based Psychoeducation (Behavioral): A brief text or video based psychoeducation message delivered via the smartphone app. Content covers the nature of emotions and emotion regulation strategies, aimed at improving emotional awareness and coping skills in the moment.
• Neutral Control Message (Behavioral): A brief text or video based message containing random facts delivered via the MetricWire smartphone app. This serves as an active control condition to allow comparison with the active intervention conditions.

Primary outcomes

• Retention Rate [10 weeks]: Proportion of enrolled participants who completed the full 10 week study protocol, including both Phase 1 and Phase 2.
• EMA Completion Rate [10 weeks]: Proportion of ecological momentary assessment (EMA) prompts answered by participants out of the total number delivered during Phase 1 and Phase 2.
• Participant Acceptability and Satisfaction [Week 10]: Participant acceptability and satisfaction with the study app and intervention content, assessed through a structured qualitative exit interview and feedback questionnaire at the end of the study.

Secondary outcomes

• Proximal Change in Negative Affect [4 weeks]: Change in self reported negative affect from pre to post intervention phone-based ecological momentary assessment at each randomization event during the micro-randomized trial. Negative affect is assessed using a visual analog scale (0 to 100) measuring sadness, anxiousness, irritability, and rumination. Active intervention conditions (mindfulness and psychoeducation) are compared to neutral control conditions to generate preliminary effect size estimates.
• Patient Health Questionnaire-8 (PHQ-8) [4 weeks]: All participants complete the Patient Health Questionnaire-8 (PHQ-8), an 8-item self-report measure of depressive symptom severity, at the start and at the end of the study. Each item is rated on a scale of 0 (not at all) to 3 (nearly every day), with total scores ranging from 0 to 24. Higher scores indicate greater depressive symptom burden.
• Generalized Anxiety Disorder-7 (GAD-7) [4 weeks]: All participants complete the Generalized Anxiety Disorder-7 (GAD-7), a 7-item self-report measure of anxiety symptom severity, at the start and at the end of the study. Each item is rated on a scale of 0 (not at all) to 3 (nearly every day), with total scores ranging from 0 to 21. Higher scores indicate greater anxiety symptom burdens.

Sex: All, ages: 18 Years to 50 Years

Inclusion Criteria:

* Age 18-50 years
* History of DSM-5 psychotic disorder (e.g., schizophrenia, schizoaffective disorder, psychosis not otherwise specified)
* Current elevated mood symptoms, defined as mild or greater depressive symptoms (Patient Health Questionnaire-8 score ≥5) or anxiety symptoms (Generalized Anxiety Disorder-7 score ≥5)
* Own a personal iPhone or Android smartphone
* Willing and able to provide informed consent
* English-speaking

Exclusion Criteria:

* Active suicidal ideation with both intent and a specific plan.
* Current substance use disorder requiring acute treatment
* Diagnosis of neurodevelopmental disorder that would impair ability to use smartphone app or complete study procedures
* Traumatic brain injury with significant cognitive impairment