Dr. Schultebraucks applies machine learning to capture the high-dimensionality of candidate predictive models for clinical outcomes. The overall goal is to develop scalable algorithms that can be used to support clinical decision-making by complementing the clinical perspectives of clinicians with data-driven prediction models. In particular, she investigates naturalistic, longitudinal and prospective studies to identify complex sets of early predictors for stress pathologies after traumatic events. Our research develops predictive models for PTSD using data routinely collected in the Emergency Room. In addition, she is working on projects to identify risk factors in high risk populations such as veterans of the US military or United Nations workforce from around the world. She is also using advanced machine learning methods, such as deep learning to identify transdiagnostic multi-model markers of maladaptive stress response using digital phenotyping.