Temporally-Informed Random Forests for Suicide Risk Prediction

Abstract

Background. Suicide is one of the leading causes of death worldwide, yet clinicians find it difficult to reliably identify individuals at high risk for suicide. Algorithmic approaches for suicide risk detection have been developed in recent years, mostly based on data from electronics health records (EHRs). These models typically do not optimally exploit the valuable temporal information inherent in these longitudinal data. Methods. We propose a temporally enhanced variant of the Random Forest model - Omni-Temporal Balanced Random Forests (OTBRFs) - that incorporates temporal information in every tree within the forest. We develop and validate this model using longitudinal EHRs and clinician notes from the Mass General Brigham Health System recorded between 1998 and 2018, and compare its performance to a baseline Naive Bayes Classifier and two standard versions of Balanced Random Forests. Results. Temporal variables were found to be associated with suicide risk. RF models were more accurate than Naive Bayesian classifiers at predicting suicide risk in advance (AUC=0.824 vs. 0.754 respectively). The OT-BRF model performed best among all RF approaches (0.339 sensitivity at 95% specificity), compared to 0.290 and 0.286 for the other two RF models. Temporal variables were assigned high importance by the models that incorporated them. Discussion. We demonstrate that temporal variables have an important role to play in suicide risk detection, and that requiring their inclusion in all random forest trees leads to increased predictive performance. Integrating temporal information into risk prediction models helps the models interpret patient data in temporal context, improving predictive performance.