Depression screening using mobile phone usage metadata: a machine learning approach

Abstract

Objective Depression is currently the second most significant contributor to non-fatal disease burdens globally. While it is treatable, depression remains undiagnosed in many cases. As mobile phones have now become an integral part of daily life, this study examines the possibility of screening for depressive symptoms continuously based on patients’ mobile usage patterns. Materials and Methods 412 research participants reported a range of their mobile usage statistics. Beck Depression Inventory—2nd ed (BDI-II) was used to measure the severity of depression among participants. A wide array of machine learning classification algorithms was trained to detect participants with depression symptoms (ie, BDI-II score ≥ 14). The relative importance of individual variables was additionally quantified. Results Participants with depression were found to have fewer saved contacts on their devices, spend more time on their mobile devices to make and receive fewer and shorter calls, and send more text messages than participants without depression. The best model was a random forest classifier, which had an out-of-sample balanced accuracy of 0.768. The balanced accuracy increased to 0.811 when participants’ age and gender were included. Discussions/Conclusion The significant predictive power of mobile usage attributes implies that, by collecting mobile usage statistics, mental health mobile applications can continuously screen for depressive symptoms for initial diagnosis or for monitoring the progress of ongoing treatments. Moreover, the input variables used in this study were aggregated mobile usage metadata attributes, which has low privacy sensitivity making it more likely for patients to grant required application permissions.

Examining the Correlation Between Depression and Social Behavior on Smartphones Through Usage Metadata: Empirical Study

“…While a smartphone is essential for communication and interpersonal interaction, it may make people less engaged with their real-life social environment [ 23 - 25 ]. Several studies found that depressed users have been reported to make fewer calls, but send more SMS text messages [ 26 - 28 ]. Kim et al [ 22 ] found that depressed users may rely on smartphones to alleviate their negative feelings and spend more time on communication, which in turn can deteriorate into problematic outcomes.…”

Potential Applications of Mobile and Wearable Devices for Psychological Support During the COVID-19 Pandemic: A Review

“…Razavi et al proposed a method of depression screening from mobile phone usage without the measurement of physical activity and movement patterns [76]. 412 participants reported a range of smartphone usage statistics, and Beck Depression Inventory-2 nd Ed (BDI-II) was used to measure the severity of depression among the participants.…”

Grant Report on SCH: Personalized Depression Treatment Supported by Mobile Sensor Analytics

“…It is led by Dr. Bing Wang, Dr. Jinbo Bi and Dr. Alexander Russell from UConn and Dr. Jayesh Kamath from UCHC. The project is broadly related to the studies that use smartphones and wearable devices to monitor, manage and assist the treatment of affective disorders (see reviews in [26][27][28][29][30][31][32]). As an example, MONARCA I and II trials feature patient self-monitoring using both objective sensory data and subjective self-assessment on smartphones; in addition, the data can be visualized on a web portal that can be accessed by both patients and clinicians [39,40].…”

“…Several reports provide evidence of feasibility and potential efficacy of using smartphone based data for clinical inferences in the management of affective disorders, primarily depression and bipolar disorder (by our team and other research groups, see reviews in [26][27][28][29][30][31][32]). Specifically, in the LifeRhythm Project, a 4-year project funded by the National Science Foundation, our group conducted a two-phase study in college age participants with depression (in comparison with a control group).…”