SIMON: A Digital Protocol to Monitor and Predict Suicidal Ideation

Each year, more than 800,000 persons die by suicide, making it a leading cause of death worldwide. Recent innovations in information and communication technology may offer new opportunities suicide prevention individuals, hereby potentially reducing this number. In our project, we design digital indices based on both self-reports passive mobile sensing test their ability to predict suicidal ideation, major predictor for psychiatric hospital readmission high-risk individuals: patients after discharge who were admitted the context ideation or attempt, expressed ideations during intake. Specifically, two smartphone applications -one (SIMON-SELF) one (SIMON-SENSE)- are installed participants' smartphones. SIMON-SELF uses text-based chatbot, called Simon, guide participants along study protocol ask questions about relevant other psychological variables five times day. These self-report data collected four consecutive weeks discharged from hospital. SIMON-SENSE collects behavioral -such as physical activity, location, social connectedness- parallel first application. We aim include 100 over 12 months whether (1) implementation such population is feasible, (2) if can be predicted using combination sensor information. To end, predictive algorithm various learning algorithms (e.g., random forest support vector machines) multilevel models will constructed. Data basis theory phenotyping may, future results, help reach vulnerable individuals early provide links just-in-time cost-effective interventions establish prompt mental health service contact. The current effort thus lead saving lives significantly reduce economic impact decreasing inpatient treatment days lost inability.