A Stochastic Compartmental Model of Suicide Risk Dynamics in U.S. Veterans

TL;DR

This paper introduces a stochastic differential equation model to simulate suicide risk dynamics among U.S. veterans, accounting for mental health transitions influenced by stress and clinical factors, and highlights potential early warning signals.

Contribution

The study develops a novel stochastic model incorporating stress processes and clinical data to better understand and predict suicide risk trajectories in veterans.

Findings

Risk-loaded individuals show persistent ideation and attempts.

Early warning signals can be identified through phase plane analysis.

Individualized dynamical models improve suicide risk assessment.

Abstract

We present a stochastic differential equation model of suicidal progression in U.S. veterans, simulating transitions across mental health states under dynamic stress and covariate influence. Transition rates are modulated by an Ornstein-Uhlenbeck stress process and clinical features derived from retrospective case-control data. Simulations reveal profile-dependent tipping behavior, with risk-loaded individuals exhibiting persistent ideation and attempt states. Area-under-the-curve and phase plane analyses suggest early warning signals and support the use of individualized dynamical models for suicide risk assessment.