Additional file 1 of Identifying individuals with undiagnosed post-traumatic stress disorder in a large United States civilian population – a machine learning approach

Additional file 1. Features used in the development of the random forest model. The “Full list” tab includes all 490 features that were available for modeling. This full list is broken down by category in the “Trauma indicators”, “Symptoms and complications”, “Other diagnoses”, and “Medications” tabs, which provide a description of how each predictor was defined. The “Importance scores” tab includes the 324 predictive features that were used to train the final random forest model (with the corresponding importance scores).