Artificial intelligence may predict opioid use disorder, research shows

The machine learning model analyzed health data from nearly 700,000 patients in Alberta who received opioid prescriptions between 2014 and 2018, cross-referencing 62 factors such as the number of doctor and emergency room visits, diagnoses, and sociodemographic information. Researchers found the top risk factors for opioid use disorder included frequency of opioid use, high dosage, and a history of other substance use disorders. The model predicted high-risk patients with an accuracy of 86 per cent when it was validated against a new sample of 316,000 patients from 2019. According to the study, the findings suggest early detection of opioid use disorder is possible with a data-driven approach and may provide timely clinical intervention and policy changes to help curb the current crisis. "It's important that the model's prediction of whether someone will develop opioid use disorder is interpreted as a risk instead of a label," said first author Yang Liu, a post-doctoral fellow in psychiatry, in the release.