Feasibility and correlations of smartphone meta-data toward dynamic understanding of depression and suicide risk in...

We investigate whether meta-data, specifically duration of responses to smartphone-delivered surveys, is correlated to elevated scores on the depression assessment PHQ-9 as well as the specific item around self-harm (item 9).

In this observational study, we recruited 92 smartphone-owning adults (≥ 18) with schizophrenia (45) and healthy controls (43). We installed an open-source smartphone app called mindLAMP to collect survey results and latencies (response times) over a period of 3 months. Surveys were scheduled for twice a week, but participants were instructed to take the surveys naturally as much or as little as they wanted. A total of 1,218 PHQ-9 surveys were completed across all participants over 3 months.

A total of 75 participants (39 with schizophrenia and 36 healthy controls) completed both the initial visit and follow-up, as well as provided at least one self-reported PHQ-9 survey through the app. We found that depression symptom severity and response latencies were correlated for both individuals with schizophrenia (Spearman's ρ = .22, p = .037) and healthy controls (Spearman's ρ = .58, p < .001). Participants with schizophrenia scored higher (more severe) and took longer for every item of the PHQ-9 when compared to controls (p < .05 for each item). Item 9 response value and latency was slightly correlated for participants with schizophrenia (Spearman's ρ = .086, p = .035) but was not significant for controls (Spearman's ρ = .036, p = .37).

Meta-data revealed group differences between individuals with schizophrenia and healthy controls based on individual depression symptoms completed on a smartphone. Correlation between suicide specific question latency and severity for participants with schizophrenia but not for controls indicates the clinical potential and need for further research.