News: AI screening tool may be able to identify patients at risk for opioid use disorder

The National Institutes of Health (NIH) recently released a study that found an artificial intelligence (AI) screening tool was as effective as healthcare providers in identifying hospitalized adults at risk for opioid use disorder (OUD) and referring them to inpatient addiction specialists, JustCoding reported.

AI also has the potential to reduce readmissions. Compared with patients who only received consultations with providers, patients screened by AI had a 43% lower chance of hospital readmission within 30 days after their initial discharge, saving nearly $109,000 in care costs during the study period.

Screening for OUD in hospitals remains inconsistent and as a result, hospitalized patients with OUD frequently leave the hospital before seeing an addiction specialist, a factor linked to a tenfold increase in overdose rates, according to an outside population-based cohort study. The AI screener was built to analyze documentation available in electronic health records to identify OUD patterns early on in visits so that an alert could be issued to providers when they opened the patient's medical chart. The alert would recommend an addiction medicine consultation and monitoring and treatment of withdrawal symptoms.

The study showed that 1.51% of hospitalized adults received an addiction medicine consultation when healthcare professionals used the AI screening tool, compared to 1.35% without AI assistance. The screener was also associated with fewer 30-day readmissions, with approximately 8% of hospitalized adults screened with AI being readmitted to the hospital compared to 14% who experienced traditional provider-led consultations.

The study suggests AI investments can be an effective strategy for healthcare systems seeking to increase access to addiction treatment while improving efficiencies and saving costs, but the authors of the study note challenges remain, including potential alert fatigue among providers and the need for broader validation across different healthcare systems. For more information on the study, visit the NIH Clinical Trials website.

Editor’s note: This article originally appeared in JustCoding. To read the full NIH study, click here.