⚡ Quick Summary
This study evaluated the effectiveness of an AI-driven screening tool for identifying hospitalized adults at risk for opioid use disorder (OUD). The results indicated that the AI screener was non-inferior to traditional methods in facilitating addiction medicine consultations while also reducing 30-day readmissions.
🔍 Key Details
- 📊 Study Design: Pre-post quasi-experimental study
- 🧩 Technology: AI screener using a convolutional neural network
- 🏥 Setting: Hospitalized adults
- 📅 Study Duration: 16-month pre-intervention phase, 8-month post-intervention phase
- 💰 Cost Analysis: Incremental cost of US$6,801 per readmission avoided
🔑 Key Takeaways
- 🤖 AI technology can effectively identify patients at risk for OUD.
- 📈 Non-inferiority of AI screener compared to usual care was established (1.35% vs. 1.51%, P < 0.001).
- 📉 Reduction in 30-day readmissions was observed (odds ratio: 0.53, P = 0.02).
- 💡 Scalable solution for hospitals to implement routine screening for OUD.
- 🏆 Potential for cost-effectiveness in managing OUD care.
- 🗓️ ClinicalTrials.gov Identifier: NCT05745480.
📚 Background
Opioid use disorder (OUD) is a significant public health concern, particularly among hospitalized adults who are at a higher risk for complications and repeated admissions. Despite the pressing need for early identification and intervention, routine screening for OUD is not standard practice in many healthcare settings. The integration of electronic health records (EHRs) and advancements in artificial intelligence (AI) present a promising opportunity to enhance the identification of at-risk patients and facilitate timely interventions.
🗒️ Study
The study aimed to assess the effectiveness of an AI-driven OUD screener embedded within the EHR system. By analyzing EHR notes in real-time, the AI tool identified patients at risk for OUD and recommended consultations with addiction medicine specialists. The primary focus was to determine whether this AI approach could match the effectiveness of traditional, human-led consultations while offering a more scalable solution.
📈 Results
The findings revealed that the AI screener was non-inferior to usual care in terms of facilitating consultations with addiction specialists. The proportion of patients who completed consultations remained consistent across both phases of the study. Additionally, the AI screener was associated with a significant reduction in 30-day readmissions, indicating its potential to improve patient outcomes while being a cost-effective solution for healthcare systems.
🌍 Impact and Implications
The implications of this study are profound. By leveraging AI technology, hospitals can implement a systematic approach to screen for OUD, potentially transforming the landscape of addiction care. This scalable solution not only enhances patient identification but also contributes to reducing healthcare costs associated with readmissions. The integration of AI in clinical settings could pave the way for improved patient outcomes and more efficient healthcare delivery.
🔮 Conclusion
This study highlights the transformative potential of AI in the identification and management of opioid use disorder among hospitalized adults. By demonstrating that an AI-driven screener can effectively match traditional methods while also reducing readmissions, it opens the door for broader applications of AI in healthcare. Continued research and implementation of such technologies could significantly enhance the quality of care for patients at risk for OUD.
💬 Your comments
What are your thoughts on the use of AI for screening opioid use disorder in hospitals? We would love to hear your insights! 💬 Leave your comments below or connect with us on social media:
Clinical implementation of AI-based screening for risk for opioid use disorder in hospitalized adults.
Abstract
Adults with opioid use disorder (OUD) are at increased risk for opioid-related complications and repeated hospital admissions. Routine screening for patients at risk for an OUD to prevent complications is not standard practice in many hospitals, leading to missed opportunities for intervention. The adoption of electronic health records (EHRs) and advancements in artificial intelligence (AI) offer a scalable approach to systematically identify at-risk patients for evidence-based care. This pre-post quasi-experimental study evaluated whether an AI-driven OUD screener embedded in the EHR was non-inferior to usual care in identifying patients for addiction medicine consultations, aiming to provide a similarly effective but more scalable alternative to human-led ad hoc consultations. The AI screener used a convolutional neural network to analyze EHR notes in real time, identifying patients at risk and recommending consultations. The primary outcome was the proportion of patients who completed a consultation with an addiction medicine specialist, which included interventions such as outpatient treatment referral, management of complicated withdrawal, medication management for OUD and harm reduction services. The study period consisted of a 16-month pre-intervention phase followed by an 8-month post-intervention phase, during which the AI screener was implemented to support hospital providers in identifying patients for consultation. Consultations did not change between periods (1.35% versus 1.51%, P < 0.001 for non-inferiority). In secondary outcome analysis, the AI screener was associated with a reduction in 30-day readmissions (odds ratio: 0.53, 95% confidence interval: 0.30-0.91, P = 0.02) with an incremental cost of US$6,801 per readmission avoided, demonstrating its potential as a scalable, cost-effective solution for OUD care. ClinicalTrials.gov registration: NCT05745480 .
Author: [‘Afshar M’, ‘Resnik F’, ‘Joyce C’, ‘Oguss M’, ‘Dligach D’, ‘Burnside ES’, ‘Sullivan AG’, ‘Churpek MM’, ‘Patterson BW’, ‘Salisbury-Afshar E’, ‘Liao FJ’, ‘Goswami C’, ‘Brown R’, ‘Mundt MP’]
Journal: Nat Med
Citation: Afshar M, et al. Clinical implementation of AI-based screening for risk for opioid use disorder in hospitalized adults. Clinical implementation of AI-based screening for risk for opioid use disorder in hospitalized adults. 2025; (unknown volume):(unknown pages). doi: 10.1038/s41591-025-03603-z