AI Screening Tool Proves Effective in Identifying and Treating Opioid Use Disorder in Hospitals

Clinical implementation of AI-based screening for risk for opioid use disorder in hospitalized adults - Nature Medicine

The primary outcome of this study was the proportion of adult hospitalizations that resulted in a completed addiction medicine consultation involving outpatient treatment referral, complicated withdrawal management, medication management for OUD or harm reduction services. During the post-intervention period, the AI screener served as the intervention, identifying patients at high risk for OUD and providing a recommendation for consultation with the addiction medicine service, along with prompting the initiation of the Clinical Opiate Withdrawal Scale and order set. Using a pre-post study design, we conducted a non-inferiority test to assess whether the addition of the AI screener could match the effectiveness of the pre-period's provider-driven ad hoc consultation workflow, while providing a scalable and automated alternative to human-led processes. The secondary outcome included the rehospitalization rate between the periods, along with a cost-effectiveness analysis of the AI screener. The AI screener comprised the AI prediction model, its real-time integration into the EHR and the recommendation for consultation with the inpatient addiction medicine service and withdrawal management orders, delivered as a best practice alert (BPA) to any hospital provider upon opening the patient's chart. Before the AI screener's hospital-wide deployment, a hybrid effectiveness-implementation framework was applied. Interviews were conducted with advanced practice providers, residents and attending physicians from surgery, internal medicine and family medicine to identify potential barriers to using the AI screener. Using the Consolidated Framework for Implementation Research to guide the interviews and Expert Recommendations for Implementing Change, barriers were addressed through additional educational initiatives, including newsletters and instructional flyers for care teams. To further optimize utilization, two rapid Plan-Do-Study-Act (PDSA) cycles were conducted between December 2022 and February 2023. The first cycle aimed to reduce the latency of the BPA and minimize the need for ad hoc addiction consult orders. The AI screener workflow was updated to incorporate notes from the emergency department, allowing for an earlier opportunity to reach the BPA threshold for a positive screen. The second PDSA cycle aimed to improve the information provided to addiction medicine specialists regarding the reason for consultation. Based on focus group feedback, the BPA was updated to preselect the Clinical Opiate Withdrawal Scale for cases where withdrawal symptoms were a potential concern, allowing for the simultaneous ordering of the consultation and the Clinical Opiate Withdrawal Scale and associated treatment order set. This update increased cases where both the Clinical Opiate Withdrawal Scale assessment and addiction medicine consultations were ordered simultaneously over a 4-week test period (P < 0.02). Following these cycles, interviews were administered to providers who interacted with the BPA to evaluate its acceptability and usability. Six respondents, comprising two hospitalist physicians, an internal medicine resident, an advanced practice provider, a family medicine physician and a surgical resident, reported that the BPA was a helpful recommendation that did not disrupt their workflow. Positive feedback emphasized the BPA's effectiveness as a prompt for identifying at-risk patients without disrupting clinical workflows. While some providers expressed concerns about alert fatigue, particularly in high-demand settings, the majority valued the screener's capacity to highlight patients who might otherwise have been overlooked. Overall, the BPA was well received by users. Following these refinements, the AI screener was successfully implemented and deployed into production hospital wide. The inclusion criteria were all adults hospitalized at the University of Wisconsin Hospital (UW Health). Patients were excluded if no clinical documentation in the EHR was recorded. The study included 51,760 adult hospitalizations, with 66% occurring during the pre-intervention period and 34% during the post-intervention period. The AI screener was deployed from 1 March 2023 to 31 October 2023, following two seasonally matched pre-intervention periods (1 March 2021-31 October 2021 and 1 March 2022-31 October 2022). A total of 727 addiction medicine consultations were completed during the entire study period (Fig. 1). No clinical adverse events related to the study were recorded from the first patient on 1 March 2021, through the last patient on 31 October 2023. Hospitalized adults in the pre-intervention period were more likely to have chronic conditions such as hypertension, diabetes and liver disease (P < 0.01) and exhibited higher Elixhauser comorbidity scores and longer hospital stays (P < 0.01). Additionally, a higher proportion of International Classification of Diseases (ICD)-10 drug misuse diagnosis codes were recorded during the pre-intervention period (P < 0.01). There were no differences in hospital readmission rates between the two periods when examining all hospitalized adults (P = 0.75; Table 1). In the subgroup of patients who received an addiction medicine consultation, demographic characteristics were similar, with few differences in comorbidities, but there was a lower proportion of unhealthy alcohol use and a higher proportion of cannabis use in the post-period (Table 2). In the first 72 h of admission, the median time to an addiction medicine consult order was longer in the post-period than pre-period (11.7 h versus 8.4 h, P < 0.001), but the overall median length of stay was similar (4.6 days versus 4.2 days, P = 0.79). As care teams entered EHR notes, the AI screener dynamically recalculated the model's score in real time, integrating all available clinical documentation up to that moment. The BPA was triggered whenever a provider accessed the patient's chart, contingent upon the AI model's score exceeding the predefined threshold. However, the BPA was automatically deactivated if it was entered into the EHR as inappropriate by the provider or an addiction medicine consult order was placed. A total of 4,328 BPAs were triggered by the AI model across 157 hospitalizations, with a median of 10 BPAs per hospitalization (interquartile range (IQR) 4-23). Among these 157 hospitalizations, 21.7% (n = 34) directly resulted in an addiction medicine consultation, as documented by the ordering provider in the EHR. The BPA-attributed consultations accounted for 12.7% (n = 34 of 267) of all addiction medicine consultations in the post-intervention period. It is important to note that the BPA may have also indirectly influenced provider decision-making, leading to consultations that were not explicitly documented in the EHR as attributable to the BPA. The majority of BPAs (90.6%, n = 3,789) were dismissed without a documented reason. The remaining dismissals were attributed to perceived inappropriateness (2.7%, n = 102), deferred action (2.6%, n = 98), canceled consult orders (2.6%, n = 97), involvement of a non-primary team (1.0%, n = 38) and other reasons (0.5%, n = 20). The Clinical Opiate Withdrawal Scale and order set for withdrawal management were ordered in 108 hospitalizations, with 29 cases (26.9%) directly triggered by the BPA. The finalized version of the BPA is shown in Fig. 2. An example of an EHR note, along with the feature importance scores for the most important medical concepts identified by the AI screener, is shown in Fig. 3. For the primary outcome, only consult orders that led to a full addiction medicine consultation visit were included. Each completed consultation was identified by an authored consultation note in the EHR from an addiction medicine specialist and an opioid-related ICD-10 code associated with the service provided. This approach was applied to both the pre-intervention and post-intervention periods for direct comparison. In the post-intervention period, an integrated daily workbench report was implemented within the EHR to allow research staff to track all hospitalizations and verify that consultations resulted in a documented intervention, such as medication for OUD, outpatient treatment referral, complicated withdrawal management or harm reduction services. This additional auditing process confirmed that interventions were completed and represented accurately in the EHR. During the post-intervention period, 1.51% of hospitalized adults received an addiction medicine consultation compared to 1.35% in the pre-intervention period (z = -1.49, P < 0.001 for non-inferiority). The adjusted odds ratio (aOR) for receiving an opioid-related addiction medicine consult after intervention was 1.09 (95% confidence interval (CI): 0.93-1.28), indicating comparable odds between the two periods after adjusting for age, sex, race/ethnicity, insurance status and comorbidity score. Similarly, 0.71% of patients received medication for OUD after intervention, compared to 0.76% before intervention (z = 0.69, P < 0.001 for non-inferiority), with an aOR of 0.87 (95% CI: 0.69-1.09). All adjusted variables and results are shown in Supplementary Tables 1 and 2. The AI screener's implementation was associated with a reduction in 30-day readmission rates among patients who received an addiction medicine consultation, with an aOR of 0.53 (95% CI: 0.30-0.91, P = 0.02). This mixed-effects analysis included a random intercept for repeat hospitalizations by the same patient and adjusted for age, sex, race/ethnicity, insurance status and comorbidity score. Additionally, there was a reduced aOR of 0.67 (95% CI: 0.47-0.94, P = 0.02) for any 30-day post-discharge hospitalization or emergency department visit. In a sensitivity analysis limited to a single hospitalization per patient, a reduction in 30-day readmission rate was still observed among patients who received an addiction medicine consultation, with an aOR of 0.36 (95% CI: 0.24-0.88, P = 0.02). There was also a reduction in any 30-day post-discharge hospital or emergency department visit, with an aOR of 0.60 (95% CI: 0.47-0.87, P = 0.01). Importantly, there was no change in the overall 30-day readmission rate when examining all adult hospitalizations during the same study period (aOR 1.00, 95% CI: 0.94-1.07, P = 0.99). All adjusted variables and results are shown in Supplementary Tables 3-5. The cost-effectiveness analysis estimated the incremental costs of the AI screener during the 8 months following its implementation (1 March 2023-31 October 2023) compared to the corresponding 8-month period in the 2 years prior. This analysis evaluated the incremental costs in relation to the intervention's effectiveness in achieving both primary and secondary outcomes. The development and implementation of the AI screener incurred several costs. Personnel expenses for building the AI model into the EHR included one principal analytics consultant, one senior analytics consultant, one data scientist, two machine learning engineers and one data science and machine learning architect. The EHR build began in October 2020 and continued until completion in January 2023. On average, the AI screener development required approximately 0.65 full-time equivalent personnel over 28 months, with total personnel salary and benefits amounting to US$234,300. The cost for storage and computing equipment during the development phase was estimated at US$109,800. Additionally, training hospital providers and addiction medicine specialists on the use of the AI screener incurred a total training cost of US$11,600. In total, the development and implementation expenses reached US$355,700. The resource costs used for developing and implementing the AI screener are detailed in Supplementary Table 6. The post-intervention incremental costs included ongoing storage and computation expenses, support for natural language processing (NLP) and machine learning components, staff time associated with screening, counseling initiated by the screener, and incremental costs for medications for OUD. The estimated incremental personnel costs for supporting the AI screener during the post-intervention period were US$101,400, with additional storage and computing costs of US$2,800. Hospital and counseling staff time, as well as medication expenses, contributed another US$1,900, bringing the total incremental costs to US$106,100 for the post-intervention period. Given that 267 patients received an addiction medicine consultation during this period, the incremental cost per patient was calculated at US$397. The AI screener's effectiveness in reducing 30-day readmission was notable, with a 5.8 percentage point difference between pre-intervention and post-intervention rates of 30-day readmission (13.7% and 7.9%, respectively). This equated to an estimated reduction of 15.6 readmissions (95% CI: 2.1-27.1) in the post-intervention period compared to the pre-intervention baseline. Consequently, the incremental cost-effectiveness ratio was determined to be US$6,801 (95% CI: US$3,915-50,524) for each 30-day readmission avoided, indicating an economic benefit of the AI screener in lowering rehospitalization rates.

NIH trial demonstrates AI's effectiveness in opioid use disorder care

National Institutes of HealthApr 3 2025 NIH-supported clinical trial shows AI tool as effective as healthcare providers in generating referrals to addiction specialists. An artificial intelligence (AI)-driven screening tool, developed by a National Institutes of Health (NIH)-funded research team, successfully identified hospitalized adults at risk for opioid use disorder and recommended referral to inpatient addiction specialists. 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. Compared to patients who received provider-initiated consultations, patients with AI screening had 47% lower odds of being readmitted to the hospital within 30 days after their initial discharge. This reduction in readmissions translated to a total of nearly $109,000 in estimated healthcare savings during the study period. The study, published in Nature Medicine, reports the results of a completed clinical trial, demonstrating AI's potential to affect patient outcomes in real-world healthcare settings. The study suggests investment in AI may be a promising strategy specifically for healthcare systems seeking to increase access to addiction treatment while improving efficiencies and saving costs. Addiction care remains heavily underprioritized and can be easily overlooked, especially in overwhelmed hospital settings where it can be challenging to incorporate resource-intensive procedures such as screening. AI has the potential to strengthen implementation of addiction treatment while optimizing hospital workflow and reducing healthcare costs." Nora D. Volkow, M.D., Director, NIH's National Institute on Drug Abuse (NIDA) In a clinical trial, researchers at the University of Wisconsin School of Medicine and Public Health, Madison, compared physician-led addiction specialist consultations to the performance of their AI screening tool, which had been developed and validated in prior work. Researchers first measured the effectiveness of provider-led consultations at the University Hospital in Madison, Wisconsin, between March to October 2021 and March to October 2022, whereby healthcare providers conducted ad hoc addiction specialist consultations for opioid use disorder. They then implemented the AI screening tool between March to October 2023 to assist the healthcare providers and remind them throughout hospitalization of a patient's need for an addiction specialist's care. From start to finish, the trial screened 51,760 adult hospitalizations, with 66% occurring without deploying the AI screener and 34% with the AI screener deployed hospital-wide. A total of 727 addiction medicine consultations were completed during the study period. The AI screener was built to recognize patterns in data, like how our brains process visual information. It analyzed information within all the documentation available in the electronic health records in real time, such as clinical notes and medical history, to identify features and patterns associated with opioid use disorder. Upon identification, the system issued an alert to providers when they opened the patient's medical chart with a recommendation to order addiction medicine consultation and to monitor and treat withdrawal symptoms. The trial found that AI-prompted consultation was just as effective as provider-initiated consultation, ensuring no decrease in quality while offering a more scalable and automated approach. Specifically, 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. Additionally, the AI screener was associated with fewer 30-day readmissions, with approximately 8% of hospitalized adults in the AI screening group being readmitted to hospital, compared to 14% in the traditional provider-led group. The reduction in 30-day readmissions still held after accounting for patients' age, sex, race and ethnicity, insurance status, and comorbidities, as calculated via an odds ratio. When analyzing the results using the odds ratio, the researchers estimated a decrease of 16 readmissions by employing the AI screener. A subsequent cost-effectiveness analysis indicated a net cost of $6,801 per readmission avoided for the patient, healthcare insurer, and/or the hospital. This amounted to an estimated total of $108,800 in healthcare savings for the eight-month study period in which the AI screener was used, even after accounting for the costs of maintaining the AI software. The average cost of a 30-day hospital readmission is currently estimated at $16,300. "AI holds promise in medical settings, but many AI-based screening models have remained in the development phase, without integration into real-world settings," said Majid Afshar, M.D., lead author of the study and associate professor at the University of Wisconsin-Madison. "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." While the AI screener showed strong effectiveness, challenges remain, including potential alert fatigue among providers and the need for broader validation across different healthcare systems. The authors also note that while the various study periods - spanning multiple years - were seasonally matched, the evolving nature of the opioid crisis may have introduced residual biases. Future research will focus on optimizing the AI tool's integration and assessing its longer-term impact on patient outcomes. The opioid crisis continues to strain healthcare systems in the U.S., with emergency department admissions for substance use increasing by nearly 6% between 2022 to 2023 to an estimated 7.6 million. Opioids are the second leading cause of these visits after alcohol, but screening for opioid use disorder in hospitals remains inconsistent. As a result, hospitalized patients with opioid use disorder frequently leave the hospital before seeing an addiction specialist, a factor linked to a tenfold increase in overdose rates. AI technology has emerged as a novel, scalable tool to potentially overcome these barriers and improve opportunities for early intervention and linkage to medications for opioid use disorder, but more research is needed to understand how AI can be used effectively in healthcare settings. If you or someone you know is struggling or in crisis, help is available. Call or text 988 or chat at 988lifeline.org. To learn how to get support for mental health, drug or alcohol conditions, visit FindSupport.gov. If you are ready to locate a treatment facility or provider, you can go directly to FindTreatment.gov or call 800-662-HELP (4357). National Institutes of Health Journal reference: Afshar, M., et al. (2025). Clinical implementation of AI-based screening for risk for opioid use disorder in hospitalized adults. Nature Medicine. doi.org/10.1038/s41591-025-03603-z.