Predictive Modeling for Early Opioid Risk Identification

Only about 22% of people with OUD receive specific treatment, while most remain at high OD risk that is clinically under-identified. Sensitive and valid approach is critically needed to identify those individuals who are at risk for using opioids and would then be at increased risk for a trajectory of increasing use of prescription opioids, OUD severity, or opioid overdose. We have developed opioid risk prediction models using temporal deep learning with big EHR Data, taking advantage of large number of EHR features and sequential deep learning methods for both OD and OUD.