Months. Now, more than 12 months post-enterprise-wide deployment, over 4800 CCF clinicians have used the AI scribe

The gap

Evidence profile

Sourced from the recommendations and future work of the source papers, classified as general, drawn from work published between 2025 and 2026, spanning 3 journals. Those papers have been cited 4 times in total.

Supporting evidence — 4 representative gaps

• Advancing Patient-Centered Nursing Practices Through AI-Driven Clinical Decision Support Systems and Personalized Care Plans (2026) · International Journal of Computer Applications Technology and Research · doi

  behind each As summarised in Table 1, each AI method corresponds to practical nursing applications, from triaging emergency department arrivals to tailoring rehabilitation schedules in physiotherapy wards [15]. These methods not only enhance accuracy but also expand the range of clinical scenarios where decision support can be deployed without overwhelming staff or compromising safety. 3.3 Integration with Nursing Workflows Successful AI-CDSS implementation depends on how seamlessly it integrates into nursing workflows [14]. In most hospital settings, the primary integration point is the EHR platform, where AI-generated alerts and recommendations appear alongside conventional patient charts [16]. This co- location avoids the need for nurses to toggle between multiple systems, reducing cognitive load. For example, in medication administration, AI modules embedded within the EHR can automatically flag potential dosing errors or contraindications before the nurse finalises the order [15]. In acute care units, predictive models monitoring vital signs feed directly into bedside devices, issuing visual and auditory alerts when thresholds are crossed [13]. These alerts are to minimise unnecessary tiered interruptions while ensuring that critical warnings are acted upon immediately. Mobile health (mHealth) platforms represent another vital integration channel [17]. Through secure applications on hospital-issued tablets or smartphones, nurses can receive patient-specific care reminders, review AI-curated educational resources, and update clinical observations in real time. This mobility is particularly valuable in community health nursing, where field visits require rapid access to centralised patient data [14]. www.ijcat.com 205 International Journal of Computer Applications Technology and Research Volume 12–Issue 12, 202 – 217, 2023, ISSN:-2319–8656 DOI:10.7753/IJCATR1212.1021 and clinical Integration also involves aligning AI recommendations with established documentation protocols requirements. In many cases, AI outputs are accompanied by hyperlinks to relevant clinical guidelines, ensuring that decision support aligns with institutional policies and regulatory standards [15]. This compliance-aware design not only increases adoption but also supports audit readiness during inspections. role. Training

  generalrecommendations
  Keywords: nursing clinical integration applications alerts patient decision support workflows hospital recommendations nurses care vital ensuring
• Accelerating ambient AI scribe enterprise-scale deployment: Cleveland Clinic’s novel approach to health system-industry partnership (2026) · npj Health Systems · doi

  Vendor tools play an important role in the healthcare ecosystem. Just as the quality and workflow compatibility of a given product are essential for its acceptability among end users and healthcare system leaders, so too is a well- designed, governed, and executed deployment. However, a successful vendor-health system partnership rarely concludes at the end of a deploy- ment. Instead, the success of that partnership in the long term may rely just as much on both parties’ ongoing commitments to optimize tools and to innovate in the development of new features. CCF and the vendor continue to do so through monitoring and optimization of the ambulatory product, developing a framework for measuring multiple dimensions of value, partnering on the expansion into the emergency department and inpatient care settings and developing tools to serve other clinicians with unique workflows such as nursing. While not every health system needs to execute enterprise-wide ambulatory care deployment in such a short timeframe, CCF’s experience provides a framework for health systems seeking to evaluate and implement AI scribes at enterprise scale. 4. Olson, K. D. et al. Use of Ambient AI Scribes to Reduce Administrative 5. Burden and Professional Burnout. JAMA Netw. Open 8, e2534976 (2025). Lukac PJ, et al. Ambient AI Scribes in Clinical Practice: A Randomized Trial. NEJM AI. 2025;2. https://doi.org/10.1056/AIoa2501000 6. Bracken, A. et al. Artificial Intelligence (AI) – Powered Documentation Systems in Healthcare: A Systematic Review. J. Med Syst. 49, 28 (2025). Shah, S. J. et al. Ambient artificial intelligence scribes: physician burnout and perspectives on usability and documentation burden. J. Am. Med. Inform. Assoc. 32, 375–380 (2025). You, J. G. et al. Ambient Documentation Technology in Clinician Experience of Documentation Burden and Burnout. JAMA Netw. Open 8, e2528056 (2025). 8. 7. 9. Holmgren, A. J. et al. Ambient Artificial Intelligence Scribes and Physician Financial Productivity. JAMA Netw. Open 9, e2553233 (2026). 10. Adler-Milstein, J et al. Subjective and Objective Impacts of Ambulatory AI Scribes | AJMC. 2026. Accessed January 8, 2026. https://www.ajmc.com/view/subjective-and-objective-impacts-of- ambulatory-ai-scribes 11. Tierney, AA et al. Ambient Artificial Intelligence Scribes: Learnings after 1 Year and over 2.5 Million Uses. NEJM Catalyst. 2025;6. https:// doi.org/10.1056/CAT.25.0040 12. Elion, Inc. Elion: AI Ambient Scribes. Accessed 2025. https://elion. health/categories/ai-ambient-scribes/products?s=% 0AN4IgZglgNgLgpgJwM4gFygBwHYBsBOHHAFgFYBaMLPARjI% 0AwzzjqvLACM24ATAJgEMADBmpsBaANogsGHHAxEqZXtXIZO% 0AGOkTzk5RarKwk21AMbUQAXQC%252BVoA 13. Tierney, AA et al. Ambient Artificial Intelligence Scribes to Alleviate the Burden of Clinical Documentation. NEJM Catalyst. 2024;5. https:// doi.org/10.1056/CAT.23.0404 14. Afshar, M et al. A Pragmatic Randomized Controlled Trial of Ambient Artificial Intelligence to Improve Health Practitioner Well-Being. NEJM AI. 2025;2. https://doi.org/10.1056/AIoa2500945 15. Wright, AP et al. Enterprise-wide simultaneous deployment of ambient scribe technology: lessons learned from an academic health system. Journal of the American Medical Informatics Association. Published online, 2025:ocaf186. 16. Ha, E. et al. Evaluating the Usability, Technical Performance, and Accuracy of Artificial Intelligence Scribes for Primary Care: Competitive Analysis. JMIR Hum. Factors 12, e71434–e71434 (2025). 17. Harder, B. America’s Best Hospitals: 2025-2026 Honor Roll and Overview. U.S. News and World Report; 2025. https://health.usnews. com/health-care/best-hospitals/articles/best-hospitals-honor-roll- and-overview#:~:text=U.S.%20News%202025%2D2026%20Best, of%20Michigan%20Health%2DAnn%20Arbor

  generalfuture work
  Keywords: scribes ambient health https arti cial intelligence documentation system ambulatory care burden nejm best vendor
• Accelerating ambient AI scribe enterprise-scale deployment: Cleveland Clinic’s novel approach to health system-industry partnership (2026) · npj Health Systems · doi

  4 months. Now, more than 12 months post-enterprise-wide deployment, over 4800 CCF clinicians have used the AI scribe across more than 3.5 M encounters. In addition, CCF maintained high utilization and high success stan- dards during the enterprise roll out and beyond. This included, for example, 70% overall encounter-level utilization among established users (those clinicians who have used the scribing tool at least 50 times since deployment. Figure 3) after a full year of deployment. Encounter-level utilization — the proportion of eligible encounters in which a clinician uses the AI scribe — is a foundational metric directly tied to realizing value at scale. It is a more demanding measure than user adoption, which captures only whether a clinician has ever used the tool. In the published literature, adoption rates for AI scribes have been reported in the range of 20–42%11, and median utili- zation (IQR) as high as 52.5% (17.9–81.0%)20. Several factors are understood to limit utilization more broadly, including resistance to change, workflow heterogeneity (e.g., clinicians with a predominantly copy-forward work- flow), lack of awareness, limited quality and reliability of AI-generated notes, and underlying models that are not optimized for complex specialty use cases. CCF’s rollout plan proactively addressed as many of these underlying factors as possible, including standards set by CCF and the vendor for workflow and content quality, particularly those being developed for specialties. At enterprise volume, CCF continues to realize durable results including continued clinician satisfaction (Net Promoter Score of 60, CSAT score of 96.6%, and 60.0% of users agreeing or strongly agreeing that the tool has increased their likelihood to remain in practice). These results are outcomes that reflect deliberate organizational choices at each phase of deployment.

  generalfuture work
  Keywords: deployment utilization enterprise clinicians used high tool clinician including months scribe encounters encounter level users
• Healthcare Professionals’ perspectives on AI-driven decision support in young adult mental health: an analysis through the lens of a shared decision-making framework (2025) · Frontiers in Digital Health · cited 4× · doi

  the potential and or 4.2 Integrating AI into mental health care for shared decision making The integration of AI into clinical processes for SDM demands careful planning to ensure the inclusiveness of all stakeholders. As the traditional dual relationship between patients and healthcare professionals is evolving into a triad of partnership with AI- based decision support systems (64). Challenges arise in maintaining person-centered care, current research highlights a gap in understanding how AI can be effectively implemented to support SDM while preserving its core principles (35). Joseph- Williams et al. (65) suggest that the SDM steps can be distributed across multiple mediators, such as therapists, nurses, and AI systems, to enhance workflow efficiency. However, an over-reliance on multiple mediators risks reducing patient engagement by diluting connection with individual caregivers. the personal AI has the potential to enhance SDM by improving flexibility, fostering partnerships, and facilitating information exchange. The participants in this study highlighted the need for individualized approaches, particularly triage processes. AI-powered conversational agents, while promising in these areas (66, 67), face challenges related to safety and reliability, as generative sometimes provide inappropriate responses. Ensuring high predictability and safety remains critical for deploying these technologies in healthcare. in psychoeducation systems can and Information exchange dynamics in SDM can shift the paradigm between paternalism and consumerism, depending on the flow and direction of information (68). The participants expressed a need for both medical and personal information to flow seamlessly between patients and providers via AI support. However, barriers such as low trust in AI-guided information and anxiety over potential errors must be addressed. Addressing these concerns requires strategies to preserve patient autonomy, foster healthcare professionals on integrating AI into workflows (69–71). collaboration, human-AI train and dynamic interplay There was a gap regarding the participants’ perspectives on AI to support key SDM elements, such as deliberation, negotiation, and reaching a middle ground. AI may disrupt these interactions, shifting SDM dynamics toward either extreme (64).

  generalrecommendations
  Keywords: information support potential healthcare systems participants integrating care decision processes patients professionals challenges multiple mediators

Questions about this gap