Improving Forecasts of Suicide Attempts for Patients with Little Data

Genesis Hang, Hope Neveux, Matthew K. Nock, Yaniv Yacoby

Keywords: Mental Health, Suicide, Timeseries Forecasting, Healthcare, Gaussian Processes, Latent Variables

TL;DR: We forecast suicide attempts using Latent Similarity Gaussian Processes (LSGP) to model patient heterogeneity, enabling those with little data to leverage similar patients' trends.

Abstract: Ecological Momentary Assessment provides real-time data on suicidal thoughts and behaviors, but predicting suicide attempts remains challenging due to their rarity and patient heterogeneity. We show that single models fit to all patients perform poorly, while individualized models improve performance but still overfit to patients with limited data. To address this, we introduce Latent Similarity Gaussian Processes (LSGPs) to capture patient heterogeneity, enabling those with little data to leverage similar patients' trends. Preliminary results show promise: even without kernel-design, we outperform all but one baseline while offering a new understanding of patient similarity.

Submission Number: 98