Using Smartphone GPS Data to Detect the Risk of Adolescent Suicidal Thoughts and Behaviors.

Importance: Suicide rates among adolescents continue to rise, but there are a lack of clinical tools to predict when youths may be at risk for suicidal behaviors. Objective: To identify whether geolocation metrics, assessed through an app installed on adolescents' personal smartphones, could detect the risk of next-week suicidal events and clinically meaningful suicidal ideation. Design, Setting, and Participants: This case series study included high-risk adolescents aged 13 to 18 years reporting a current affective and/or substance use disorder, oversampled for suicidal thoughts and behaviors (STB). Participants were recruited from the greater New York City and Pittsburgh communities through psychiatric outpatient programs, emergency departments, medical center research registries, and social media. Participants installed the Effortless Assessment Research System (EARS) software application onto their personal smartphones, which obtained passive sensor data, including geolocation metrics (via the global positioning system [GPS]), as well as weekly experience sampling data probing STB for the duration of the 6-month study. Adolescents also completed clinical assessments at baseline as well as during the 1-, 3-, and 6-month follow-up assessments. Statistical analysis was performed from March 2023 to November 2024. Main Outcomes and Measures: Repeated measures mixed-effects logistic models estimated whether weekly aggregates of geolocation features (ie, entropy, homestay, distance traveled) were associated with next-week suicidal events (ie, suicide attempts, psychiatric hospitalizations, emergency department visits for suicide concerns) and clinically meaningful ideation (via weekly experience sampling). Results: Overall, 186 participants were included in this study (148 [79.6%] female; 19 [10.2%] Asian, 23 [12.4%] Black, and 106 [57.0%] White), with a mean (SD) age of 16.4 (1.7) years. Greater homestay (amount of time spent at home) on a given week, relative to one's own mean, was associated with 2-fold greater odds of suicidal events during the subsequent week (odds ratio, 1.99 [95% CI, 1.15-3.45]). Results were not significant for entropy and distance traveled metrics. However, using leave-future-out validation, the accuracy of the homestay model was modest (area under the receiver operating characteristic curve, 0.64 [95% CI, 0.50-0.78]). Conclusions and Relevance: Advancements in smartphone technology afford unique opportunities to capture affective and behavioral dynamics that presage suicide risk. This case series study found that greater homestay obtained through smartphone GPS data over the course of a week, relative to one's own mean, was associated with greater odds of a suicidal event in the subsequent week. Although accuracy was modest, these findings offer a novel starting point for suicide prevention research, particularly as smartphone sensor data may have the capacity to identify who is at risk while also providing an opportunity to deliver clinical tools when that risk is greatest.