The University of Wisconsin (UW) School of Medicine and Public Health, US, has developed an AI-driven screening tool that detects the hospitalised adult population who are at risk of opioid use disorder (OUD).
According to UW, the tool is said to “recommend” referrals to inpatient addiction specialists and claims to be equally “effective” as health provider-only approaches in starting consultations and monitoring for opioid withdrawal.
Go deeper with GlobalData
Subjects recognised by the AI screening tool for addiction medicine referrals who obtained consultations had a 47% lesser possibility of hospital readmission within 30 days post-discharge.
This minimisation resulted in significant healthcare savings during the study.
A recently published study reports the outcomes of a trial funded by the National Institutes of Health, highlighting the potential of AI to improve patient outcomes in real-world healthcare settings.
Dr Majid Afshar, the study’s principal investigator and the UW School of Medicine and Public Health medicine associate professor, noted that investing in AI could be a “promising” strategy for healthcare systems to enhance addiction treatment access, increase efficiencies, and save expenses.
US Tariffs are shifting - will you react or anticipate?
Don’t let policy changes catch you off guard. Stay proactive with real-time data and expert analysis.
By GlobalDataDr Afshar said: “Our study represents one of the first demonstrations of an AI screening tool embedded into addiction medicine and hospital workflows, highlighting the pragmatism and real-world promise of this approach.”
The tool analyses electronic health records in real time, identifying patterns associated with OUD.
According to the university, it was tailored to detect identical data patterns to how the brain processes visual data.
Upon identification, the tool alerts providers with recommendations for addiction medicine consultation, as well as for treating and monitoring withdrawal symptoms.
The tool’s effectiveness was analysed by the team by comparing data with provider-led consultations over two time periods between 2021 and 2023.
During the trial, 51,760 adult hospitalisations were screened, with two-thirds occurring before the AI screener’s deployment.
A total of 727 consultations in addiction medicine were completed, with 1.51% of hospitalised adult subjects receiving a consultation using the AI tool versus 1.35% without it.
The AI group also saw fewer 30-day readmissions, nearly 8% versus 14% in the group led by traditional providers.
The National Institute on Drug Abuse of the National Institutes of Health granted funding for the work.
