The University of Wisconsin School of Medicine and Public Health, Madison, funded by the National Institutes of Health (NIH), has created an artificial intelligence (AI) tool that can accurately screen hospitalized patients over 18 for opioid use disorder risk, according to a release.
If a patient is at risk, the tool will refer them to addiction resources. The tool was tested in a clinical trial. According to NIH’s announcement, “the AI-based method was just as effective as a health provider-only approach in initiating addiction specialist consultations and recommending monitoring of opioid withdrawal.” Patients who used the AI tool “had 47% lower odds of being readmitted to the hospital within 30 days after their initial discharge” than those who consulted a provider. This saved about $109,000.
Additionally, “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 the assistance of the AI tool.” The AI tool can detect how certain brains process vital information. It assessed patients’ electronic health records “to identify features and patterns associated with opioid use disorder” and notified their physicians.
The study is published in Nature Medicine.
