Health data used to predict who will use opioids after hospitalization

Using electronic health record data, researchers identified patient-specific variables which were highly associated with the progression to COT. These included having a history of substance use disorder, past year receipt of a benzodiazepine, receipt of an opioid at hospital discharge and high opioid requirements during hospitalization. The model correctly predicted chronic opioid therapy in 79% of the patients and no COT correctly in 78% of the patients.