Kiran Veernapu*

Manager Engineering Delivery at Intermountain Health, Salt Lake City, United States

*Corresponding Author: Kiran Veernapu, Manager Engineering Delivery at Intermountain Health, Salt Lake City, United States.

Received: November 03, 2025; Published: November 14, 2025

Abstract

Clinical documentation is everywhere in the health system, but remains a significant contributor to physician burnout due to the time and repetitive Nature of the demands it imposes upon physicians. The recent developments in the field of Artificial Intelligence (AI), including Automatic Speech Recognition (ASR), NLP, and Large Language Models (LLM), have led to the development of AI-enhanced clinical documentation systems and medical scribes that can partially automate the documentation process. These systems can capture the interaction between a clinician and a patient, transcribe the speech in real-time, and generate structured abstracts that can be saved in classic note formats (including SOAP or BIRP), significantly cutting down on the amount of administrative overhead.
Proposals of these applications, such as Nuance DAX Copilot, Suki AI, and DeepScribe, have demonstrated significant decreases in time to document and increases in coding compliance and clinician satisfaction. Nevertheless, there are still burning issues. Issues of reliability of models, language bias, security of data, and patient confidentiality still pose challenges to widespread use. Ethical and regulatory issues such as informed consent, responsibility, and fairness among various groups of users make the system-level validation necessary, and due to the safety and transparency offered by the human-in-the-loop validation.

Keywords: Clinical Documentation; Medical Scribes; Artificial Intelligence; Automatic Speech Recognition (ASR); Natural Language Processing (NLP); Large Language Models (LLMs); Electronic Health Records (EHR); Privacy; Ethics

References

1. K Patel., et al. “Evaluating Nuance DAX Copilot: Ambient AI scribe for mitigating clinician burnout”. Journal of the American Medical Informatics Association 4 (2024): 551-560.
2. A B Rao., et al. “Physician experiences with AI scribes: A qualitative multi-specialty study”. JAMA Network Open 12 (2024): e243812.
3. B Krittanawong., et al. “Integration of artificial intelligence-powered scribes into electronic health records: current state and future perspectives”. Lancet Digital Health3 (2023): e155-e167.
4. A Singhal., et al. “Large language models encode clinical knowledge”. Nature 7972 (2023): 172-180.
5. P Nori., et al. “Performance of GPT-4 on medical challenge benchmarks”. arXiv preprint arXiv:2303.13375 (2023).
6. T Lin., et al. “Evaluating automatic medical note summarization with domain-specific metrics”. in Proc. AMIA Annu. Symp (2023): 721-730.
7. J Chen., et al. “Hallucinations in large language models for healthcare applications: An empirical study”. in Proc. AAAI Conf. Artif. Intell 38.13 (2024): 14592-14601.
8. A Ali., et al. “Bias and fairness in medical LLMs: Risks and mitigation strategies”. in Proc. ACM Conf. In Fairness, Accountability, and Transparency (FAccT) (2024): 515-526.
9. T S Park., et al. “Domain-specific ASR for healthcare: Decreasing error rates in multilingual environment”. in IEEE J. Biomed. Health Inform 28.1 (2024): 22-33.
10. Microsoft Corporation. “Nuance Dragon Ambient eXperience (DAX) Copilot: AI-powered clinical documentation”. White Paper (2024).
11. Suki AI. "Next-generation AI medical scribe for clinicians”. Technical Brief (2024).
12. DeepScribe Inc., “AI-powered clinical documentation platform”. Company Report (2025).
13. A Adedeji., et al. “The sound of healthcare: Improving medical transcription ASR accuracy with large language models”. arXiv preprint arXiv:2402.07658 (2024).
14. A Biswas and W Talukdar. “Intelligent clinical documentation: Harnessing generative AI for patient-centric clinical note generation”. arXiv preprint arXiv:2405.18346 (2024).
15. C Lee., et al. “Improving clinical documentation with AI: A comparative study of Sporo AI Scribe and GPT-4o mini”. arXiv preprint arXiv:2410.15528 (2024).
16. J Seo., et al. “Evaluation framework of large language models in medical documentation: Development and usability study”. Journal of Medical Internet Research 26 (2024): e58329.
17. S Maity and M J Saikia. “Large language models in healthcare and medical applications: A review”. Bioengineering 6 (2025): 631.
18. Al Harthi., et al. “Large language models in medicine: A review of current clinical trials across healthcare applications”. Frontiers in Medicine 11 (2024): 39561120.
19. “Impact of AI scribes on streamlining clinical documentation: A systematic review”. Healthcare (MDPI)12 (2025): 1447.
20. T Zhao., et al. “Efficient healthcare with large language models: Optimizing clinical workflow and enhancing patient care”. Journal of the American Medical Informatics Association 6 (2024): 1436-1448.
21. E Müller and K Huang. “Adapting generative large language models for information extraction from unstructured EHRs in aged care: Comparative training approaches”. Journal of Healthcare Informatics Research 9 (2025): 191-219.
22. N Desai., et al. “Ethical and regulatory considerations for AI medical scribes in clinical environments”. Digital Health 11 (2025): 2055207624123456.
23. K H Oh., et al. “Privacy-preserving federated learning for medical note generation”. IEEE Trans. Neural Netw. Learn. Syst 36.2 (2025): 499-512.
24. World Health Organization (WHO). “Ethics and Governance of Artificial Intelligence for Health: Guidance for Large Language Models, Policy Paper” (2024).
25. Veernapu K. “The Implementation of AI in Clinical Decision Support System: Effects on Patient Outcomes and Operational Costs”. IJFMR 5 (2023).
26. Kiran Veernapu. “Comprehensive Analysis of HIPAA: Privacy, Security, and Compliance in the Digital Healthcare Era”. International Journal of Leading Research Publication5 (2021): 1-7.
27. S. Food and Drug Administration (FDA), Proposed Regulatory Framework for Modifications to AI/ML-Based Software as a Medical Device (SaMD), White Paper, (2024).

Citation

Citation: Kiran Veernapu. “AI-Driven Clinical Documentation and Medical Scribes". Acta Scientific Computer Sciences 7.8 (2025): 20-25.

Copyright

Copyright: © 2025 Kiran Veernapu. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.