Leveraging Longitudinal Lifelog Data Using Survival Models for Predicting Risk of Relapse among Patients with Depression in Remission

Managing depression relapse is a challenge given factors such as inconsistent follow-up and cumbersome psychological distress evaluation methods which leaves patients with a high risk of relapse to leave their symptoms untreated. In an attempt to bridge this gap, we proposed an approach on the use of personal longitudinal lifelog activity data gathered from individual smartphones of patients in remission and maintenance therapy (N=87) to predict their risk of depression relapse. Through the use of survival models, we modeled the activity data as covariates to predict survival curves to determine if patients are at risk of relapse. We compared three models: CoxPH, Random Survival Forests, and DeepSurv, and found that DeepSurv performed the best in terms of Concordance Index and Brier Score. Our results show the possibility of utilizing lifelog data as a means of predicting the onset of relapse and towards building eventual tools for a more coherent patient evaluation and intervention system.