An efficient landmark model for prediction of suicide attempts in multiple clinical settings

Growing evidence has shown that applying machine learning models to large clinical data sources may exceed clinician performance in suicide risk stratification. However, many existing prediction models either suffer from temporal bias (a bias that stems from using case-control sampling) or require training on all available patient visit data. Here, we adopt a landmark model framework that aligns with clinical practice for prediction of suicide-related behaviors (SRBs) using a large electronic health record database. Using the landmark approach, we developed models for SRB prediction (regularized Cox regression and random survival forest) that establish a time-point (e.g., clinical visit) from which predictions are made over user-specified prediction windows using historical information up to that point. We applied this approach to cohorts from three clinical settings: general outpatient, psychiatric emergency department, and psychiatric inpatients, for varying prediction windows and lengths of historical data. Models achieved high discriminative performance (area under the Receiver Operating Characteristic curve 0.74-0.93 for the Cox model) across different prediction windows and settings, even with relatively short periods of historical data. In short, we developed accurate, dynamic SRB risk prediction models with the landmark approach that reduce bias and enhance the reliability and portability of suicide risk prediction models.

Automated summary

This study finds that applying machine learning models to clinical data can outperform clinicians in suicide risk stratification. The researchers use a landmark model framework, aligned with clinical practice, and a large electronic health record database to predict suicide-related behaviors. The models developed using this approach achieve high predictive performance across different prediction windows and settings.