Population-level individualized prospective prediction of opioid overdose using machine learning

The opioid overdose epidemic has rapidly expanded in North America, with rates accelerating during the COVID-19 pandemic. No existing study has demonstrated prospective opioid overdose at a population level. This study aimed to develop and validate a population-level individualized prospective prediction model of opioid overdose (OpOD) using machine learning (ML) and de-identified provincial administrative health data. The OpOD prediction model was based on a cohort of approximately 4 million people in 2017 to predict OpOD cases in 2018 and was subsequently tested on cohort data from 2018, 2019, and 2020 to predict OpOD cases in 2019, 2020, and 2021, respectively. The model's predictive performance, including balanced accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristics Curve (AUC), was evaluated, achieving a balanced accuracy of 83.7, 81.6, and 85.0% in each respective year. The leading predictors for OpOD, which were derived from health care utilization variables documented by the Canadian Institute for Health Information (CIHI) and physician billing claims, were treatment encounters for drug or alcohol use, depression, neurotic/anxiety/obsessive-compulsive disorder, and superficial skin injury. The main contribution of our study is to demonstrate that ML-based individualized OpOD prediction using existing population-level data can provide accurate prediction of future OpOD cases in the whole population and may have the potential to inform targeted interventions and policy planning.