Both interventions produced significant gains among clients with serious and persistent mental illnesses who were mostly from racial minority groups. The mHealth intervention showed superior patient engagement and produced patient satisfaction and clinical and recovery outcomes that were comparable to those from a widely used clinic-based group intervention for illness management.

Objective This purpose of this study was to describe and demonstrate CrossCheck, a multimodal data collection system designed to aid in continuous remote monitoring and identification of subjective and objective indicators of psychotic relapse. Methods Individuals with schizophrenia-spectrum disorders received a smartphone with the monitoring system installed along with unlimited data plan for 12 months. Participants were instructed to carry the device with them and to complete brief self-reports multiple times a week. Multi-modal behavioral sensing (i.e., physical activity, geospatial activity, speech frequency and duration) and device use data (i.e., call and text activity, app use) were captured automatically. Five individuals who experienced psychiatric hospitalization were selected and described for instructive purposes. Results Participants had unique digital indicators of their psychotic relapse. For some, self-reports provided clear and potentially actionable description of symptom exacerbation prior to hospitalization. Others had behavioral sensing data trends (e.g., shifts in geolocation patterns, declines in physical activity) or device use patterns (e.g., increased nighttime app use, discontinuation of all smartphone use) that reflected the changes they experienced more effectively. Conclusion Advancements in mobile technology are enabling collection of an abundance of information that until recently was largely inaccessible to clinical research and practice. However, remote monitoring and relapse detection is in its nascency. Development and evaluation of innovative data management, modeling, and signal-detection techniques that can identify changes within an individual over time (i.e. unique relapse signatures) will be essential if we are to capitalize on these data to improve treatment and prevention.

Objective The purpose of this study was to examine the feasibility, acceptability, and utility of behavioral sensing in individuals with schizophrenia. Methods Outpatients (N=9) and inpatients (N=11) carried smartphones for two or one week periods, respectively. Device-embedded sensors (i.e., accelerometers, microphone, GPS, WiFi, Bluetooth) collected behavioral and contextual data, as they went about their day. Participants completed usability/acceptability measures rating this approach. Results Sensing successfully captured individuals’ activity, time spent proximal to human speech, and time spent in different locations. Usability and acceptability ratings showed participants felt comfortable using the sensing system (95%), and that most would be interested in receiving feedback (65%) and suggestions (65%). Approximately 20% reported that sensing made them upset. A third of inpatients were concerned about their privacy, but no outpatients expressed this concern. Conclusions Mobile behavioral sensing is a feasible, acceptable, and informative approach for data collection in outpatients and inpatients with schizophrenia.

Continuously monitoring schizophrenia patients’ psychiatric symptoms is crucial for in-time intervention and treatment adjustment. The Brief Psychiatric Rating Scale (BPRS) is a survey administered by clinicians to evaluate symptom severity in schizophrenia. The CrossCheck symptom prediction system is capable of tracking schizophrenia symptoms based on BPRS using passive sensing from mobile phones. We present results from an ongoing randomized control trial, where passive sensing data, self-reports, and clinician administered 7-item BPRS surveys are collected from 36 outpatients with schizophrenia recently discharged from hospital over a period ranging from 2-12 months. We show that our system can predict a symptom scale score based on a 7-item BPRS within ±1.45 error on average using automatically tracked behavioral features from phones (e.g., mobility, conversation, activity, smartphone usage, the ambient acoustic environment) and user supplied self-reports. Importantly, we show our system is also capable of predicting an individual BPRS score within ±1.59 error purely based on passive sensing from phones without any self-reported information from outpatients. Finally, we discuss how well our predictive system reflects symptoms experienced by patients by reviewing a number of case studies.