Development And Validation Of A Machine Learning Model Using Electronic Health Records To Predict Trauma- And Stressor-related Psychiatric Disorders After Hospitalization With Sepsis

This article reviews research on machine learning models to predict PTSD after a variety of potentially traumatic experiences. Studies have shown that machine learning models can accurately identify those at risk for PTSD after a variety of injuries. However, there are several limitations to real-world implementation, such as reliance on extensive research assessment batteries and small sample sizes. This article aims to overcome these limitations by developing and validating a predictive model that relies solely on electronic health records (EHR) data collected at the time of hospitalization to predict trauma- and stressor-related disorders (TSRD).