Skip to main content

Smartphone Logs Have Potential to Predict Relapse in Schizophrenia

April 11, 2019

By Marilynn Larkin

NEW YORK—Reductions in outgoing smartphone calls and texts are associated with relapse in individuals with schizophrenia, an exploratory study suggests.

"People with schizophrenia were less likely to send or receive text messages or spend time on outgoing calls in the 30-day period that preceded a psychiatric relapse," Dr. Benjamin Buck of the University of Washington, Seattle, told Reuters Health. "Social isolation is a risk factor for poor psychiatric outcomes. Our project adds to that knowledge by demonstrating that our phones may pick up traces of that social isolation."

"Just as data from pedometers let us know whether we've been getting steps, data from our phones can let us know whether we've been active or social," he said by email. "This information could be incredibly valuable when it indicates that a patient is at risk for relapse. When this happens, patients or providers could be prompted to act to prevent negative outcomes."

Dr. Buck and colleagues enrolled 149 individuals with schizophrenia at elevated risk for relapse. After exclusions and dropouts, data were analyzed for 61 (mean age about 37; about 60% men; 35% white) who were given smartphones with the CrossCheck behavioral sensing system for a year of remote monitoring. CrossCheck used the phone's microphone, call record, and text messaging log to capture digital socialization data. Forty-five participants fully completed the study.

As reported online March 30 in Schizophrenia Research, 20 participants experienced 27 relapse events during the study, including psychiatric hospitalization (88%), increased intensity of services (28%), increased medication (24%), suicidal ideation (16%), homicidal ideation (4%), self-injury (8%) or interpersonal violence (4%).

Reductions in the number and duration of outgoing calls, as well as the number of text messages were significantly associated with relapse within the next 30 days. By contrast, the number and duration of incoming phone calls and in-person conversations were not.

"Smartphone enabled social activity may provide an important metric in determining relapse risk in schizophrenia and provide access to sensitive, meaningful and ecologically valid data streams never before available in routine care," the authors conclude.

"So far, we've only deployed this system in a research context, but we see significant potential for developing and disseminating clinic-based sensing tools," Dr. Buck said. "It's exciting to imagine clinical care in which smartphones are used to provide additional insight into psychiatric status."

"As these technologies develop," he noted, "this information could be used to determine who is at risk and who might benefit from additional support in the moment. This could make the difference between relapse and continued recovery."

Dr. Colin Walsh, assistant professor of Biomedical Informatics at Vanderbilt University Medical Center in Nashville, said in an email to Reuters Health, "Social connectedness is important to schizophrenia and to health in general. But traditional electronic health records capture data about social functioning very poorly. Clinical visits happen sporadically and, even if providers ask about social behaviors, we lack good options to record those data in clinical records."

"It's promising to see how phone call and text message behaviors might indicate worsening periods of mental illness," he said. "It's tempting to try to interpret the results as 'cause and effect,' but they remain correlations in need of further study, as the researchers rightly state."

"Healthcare systems that let individuals opt in to sharing smartphone data to improve health have the potential to help a lot of people," he said. "They also might provide important information to providers that is almost impossible to get now in, say, a 15-minute primary care visit."

Nonetheless, he added, "Protecting privacy remains a huge challenge in approaches like this one. We need to balance potential benefits of increased, real-time monitoring with potential consequences of data breach or loss of privacy and anonymity."

"This study (also) raises important questions about how systems like this one might be designed to interface with traditional healthcare," Dr. Walsh said. "The researchers closely monitored the participants during the study. How would such monitoring scale to larger groups of people given healthcare resources are already limited in many areas? If risk of relapse or suicide is identified in real-time, do we have clinical processes in place to intervene?"

Further, he said, "A number of participants did not either agree to participate in the study or withdrew. We need a better understanding of reasons people might refuse to participate in such programs to improve on this interesting exploratory work."


Schizophr Res 2019.

(c) Copyright Thomson Reuters 2019. Click For Restrictions -

Back to Top