Artificial Intelligence Empowers Regulatory Compliance Science for Medical Devices: From Premarket Approval to Post-market Surveillance, How Far Are We There?

Engineering

Adv search

Artificial Intelligence Empowers Regulatory Compliance Science for Medical Devices: From Premarket Approval to Post-market Surveillance, How Far Are We There?

Yu-Sheng Hsueh , Regis J O'Keefe , Stuart Goodman , Péter Hegyi , R. Geoff Richards , Minghao Zheng , Wenxue Tong , Jiankun Xu , Christer Rolf , Patrick Shu-Hang Yung , Ling Qin , MRN working group

Engineering ›› : 202610012

PDF (6039KB)

Engineering ›› :202610012 DOI: 10.1016/j.eng.2026.10.012

research-article

Artificial Intelligence Empowers Regulatory Compliance Science for Medical Devices: From Premarket Approval to Post-market Surveillance, How Far Are We There?

Author information +

^a Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong , Hong Kong 999077, China

^b AoE Centre for Musculoskeletal Degeneration and Regeneration, Department of Orthopaedics & Traumatology, Faculty of Medicine, The Chinese University of Hong Kong , Hong Kong 999077, China

^c Department of Orthopaedic Surgery, School of Medicine, Washington University , St. Louis, MO 63110, USA

^d Department of Orthopedic Surgery, Stanford Medicine, Stanford University , Redwood City, CA 94305, USA

^e Centre for Translational Medicine, Semmelweis University , Budapest 1085, Hungary

^f AO Research Institute Davos , Davos 7270, Switzerland

^g Perron Institute for Neurological and Translational Science, University of Western Australia , Nedlands, WA 6009, Australia

^h Department of Clinical Science, Intervention and Technology, Karolinska Institute , Huddinge SE-141 52, Sweden

ⁱ The Musculoskeletal Regeneration Research Network (MRN) Working Group

^*E-mail addresses: lingqin@cuhk.edu.hk (L. Qin),

patrickyung@cuhk.edu.hk (P.S.-H. Yung).

Show less

History +

PDF (6039KB)

Abstract

While artificial intelligence (AI) in medicine has been extensively studied as a medical device, its role as a governance tool for regulatory authorities remains largely unexplored. The rapid influx of innovative, AI-integrated medical devices has revealed critical bottlenecks in the current human-designed regulatory system (Hud-RS), including approval delays and resource constraints. In this work, we conceptualize a comprehensive dynamic framework for regulatory modernization, termed the “Artificial Intelligence Governance Regulatory System (Aig-RS).” The framework covers the full product lifecycle, from pre-clinical and clinical review to post-market surveillance. We examine current practices across regulatory agencies and propose strategies to optimize existing measures to streamline review processes. Although the US Food and Drug Administration (FDA) has made significant advances with its agency-wide tool (enterprise language support assistant (ELSA)), timely translation of innovative medical devices into clinical practice remains limited. Accordingly, Aig-RS is intended to accelerate regulatory decision-making safely by leveraging AI and to clarify how regulatory agencies can implement AI across the review continuum.

Keywords

Artificial intelligence governance / Review and approval / Medical device / Regulatory authority / Clinical compliance

Cite this article

Download citation ▾

Yu-Sheng Hsueh, Regis J O'Keefe, Stuart Goodman, Péter Hegyi, R. Geoff Richards, Minghao Zheng, Wenxue Tong, Jiankun Xu, Christer Rolf, Patrick Shu-Hang Yung, Ling Qin, MRN working group. Artificial Intelligence Empowers Regulatory Compliance Science for Medical Devices: From Premarket Approval to Post-market Surveillance, How Far Are We There?. Engineering 202610012 DOI:10.1016/j.eng.2026.10.012

登录浏览全文

4963

注册一个新账户忘记密码

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Darrow JJ, Avorn J, Kesselheim AS . FDA regulation and approval of medical devices: 1976-2020. JAMA 2021; 326(5): 420-32.

[2]	The European Medicines Agency. Overview of medical devices and in vitro diagnostic medical devices (IVDs) [Internet]. Amsterdam: The European Medicines Agency; [cited 2025 Jul 21]. Available from: https://health.ec.europa.eu/medical-devices-sector/overview_en.

[3]	Freyer O, Jayabalan S, Kather JN, Gilbert S . Overcoming regulatory barriers to the implementation of AI agents in healthcare. Nat Med 2025; 31(10): 3239-43.

[4]	Alam M, Shi VJ, Maisel-Campbell A, Cressey BD, Nadir U, Koza E, et al. US FDA advisory panel members’ assessment of premarket approval process and suggestions for improvement. JAMA Netw Open 2024; 7(10): e2436066.

[5]	Bauchner H, Fontanarosa P . Bias among peer reviewers. JAMA 2017; 318(8): 755-6.

[6]	Link AM . US and non-US submissions: an analysis of reviewer bias. JAMA 1998; 280(3): 246-7.

[7]	The European Medicines Agency. Regulation (EU) 2024/1689 laying down harmonised rules on artificial intelligence [Internet]. Amsterdam: The European Medicines Agency; 2024 [cited 2025 Aug 18]. Available from: https://digital-strategy.ec.europa.eu/en/policies/regulatory-framework-ai.

[8]	Rajpurkar P, Chen E, Banerjee O, Topol EJ . AI in health and medicine. Nat Med 2022; 28(1): 31-8.

[9]	Wankhede PR, Bhuyar D, Zanwar S, Pawar R, Jadhav MR, Gandhewar N, et al. Artificial intelligence for noninvasive health diagnostics. ACS Sens 2025; 10(11): 8217-55.

[10]	Cuocolo R, Bernardini D, Pinto Dos Santos D, Klontzas ME, Akinci D’Antonoli T, Semedo LC, et al.; the European Society of Radiology. AI medical device post-market surveillance regulations: consensus recommendations by the European Society of Radiology. Insights Imaging 2025; 16(1): 275.

[11]	Clark P, Kim J, Aphinyanaphongs Y. Marketing and US Food and Drug Administration clearance of artificial intelligence and machine learning enabled software in and as medical devices: a systematic review. JAMA Netw Open 2023; 6(7): e2321792.

[12]	The European Medicines Agency. Artificial intelligence [Internet]. Amsterdam: The European Medicines Agency; [cited 2025 Jul 30]. Available from: https://www.ema.europa.eu/en/about-us/how-we-work/data-regulation-big-data-other-sources/artificial-intelligence.

[13]

US Food and Drug Administration. FDA launches agency-wide AI tool to optimize performance for the American people [Internet]. Silver Spring: US Food and Drug Administration; [cited 2026 May 26]. Available from: https://www.fda.gov/news-events/press-announcements/fda-launches-agency-wide-ai-tool-optimize-performance-american-people.

[14]	US Food and Drug Administration. PMA review process [Internet]. Silver Spring: US Food and Drug Administration; [cited 2025 Aug 22]. Available from: https://www.fda.gov/medical-devices/premarket-approval-pma/pma-review-process.

[15]	Shea M, Ostermann L, Hohman R, Roberts S, Kozak M, Dull R, et al. Regulatory watch: impact of breakthrough therapy designation on cancer drug development. Nat Rev Drug Discov 2016; 15(3): 152.

[16]	US Food and Drug Administration. August 27, 2025 MDUFA V performance report (FY 2023 through FY 2027) [Internet]. Silver Spring: US Food and Drug Administration; [cited 2025 Aug 28]. Available from: https://www.fda.gov/about-fda/user-fee-performance-reports/mdufa-performance-reports.

[17]	US Food and Drug Administration. Notified bodies for medical devices-European Commission [Internet]. Amsterdam: The European Medicines Agency; [cited 2025 Jul 31]. Available from: https://health.ec.europa.eu/medical-devices-topics-interest/notified-bodies-medical-devices_en.

[18]

European Commission. Study supporting the monitoring of availability of medical devices on the EU market-survey results of the 14th NB survey (MDR/IVDR) with data status 28 February 2025 [Internet]. Brussels: European Commission; [cited 2025 Aug 22]. Available from: https://health.ec.europa.eu/study-supporting-monitoring-availability-medical-devices-eu-market_en.

[19]	Stange AF, Julian E. Conformity assessment of medical devices: an overview from a notified body. J Mark Access Health Policy 2026; 14(1): 4.

[20]

US Food and Drug Administration. FDA expands AI capabilities and completes data platform consolidation [Internet]. Silver Spring: US Food and Drug Administration; [cited 2026 May 19]. Available from: https://www.fda.gov/news-events/press-announcements/fda-expands-ai-capabilities-and-completes-data-platform-consolidation.

[21]	Windecker S, Fraser AG, Szymanski P, Gilard M, Lüscher TF, Abid L, et al. Priorities for medical device regulatory approval: a report from the European Society of Cardiology Cardiovascular Round Table. Eur Heart J 2025; 46(16): 1469-79.

[22]

National Medical Products Administration. Response to proposal No. 5113 of the Second Meeting of the 14th National People’s Congress [Internet]. Beijing: National Medical Products Administration; 2024 Oct 15 [cited 2025 Aug 23]. Available from: https://www.nmpa.gov.cn/zwgk/jyta/rdjy/20241015182848162.html?type=pc&m=Chinese.

[23]	US Food and Drug Administration. Digital health policy navigator [Internet]. Silver Spring: US Food and Drug Administration; [cited 2026 Jan 20]. Available from: https://www.fda.gov/medical-devices/digital-health-center-excellence/digital-health-policy-navigator.

[24]	Medical Device Division, Department of Health, HKSAR. General medical device classification program [Internet]. Hongkong: Medical Device Division; [cited 2026 Jan 20]. Available from: https://www.mdd.gov.hk/en/mdacs/online-tools/general-medical-device-classification-program/index.html.

[25]	Suarez-Sharp S, Li M, Duan J, Shah H, Seo P . Regulatory experience with in vivo in vitro correlations (IVIVC) in new drug applications. AAPS J 2016; 18(6): 1379-90.

[26]

US Food and Drug Administration. General considerations for animal studies intended to evaluate medical devices [Internet]. Silver Spring: US Food and Drug Administration; [cited 2025 Aug 23]. Available from: https://www.fda.gov/regulatory-information/search-fda-guidance-documents/general-considerations-animal-studies-intended-evaluate-medical-devices.

[27]	Huang S, Wen J, Zhang Y, Bai X, Cui ZK . Choosing the right animal model for osteomyelitis research: considerations and challenges. J Orthop Translat 2023; 43: 47-65.

[28]	Swearengen JR . Choosing the right animal model for infectious disease research. Animal Model Exp Med 2018; 1(2): 100-8.

[29]	Cheng M, Liu W, Zhang J, Zhang S, Guo Z, Liu L, et al. Regulatory considerations for animal studies of biomaterial products. Bioact Mater 2021; 11: 52-6.

[30]	FDA pushes to replace animal testing. Nat Biotechnol 2025; 43(5): 655.

[31]	ISO. ISO/AWI 25430-1, biotechnology-organoids [Internet]. Geneva: ISO; [cited 2025 Aug 3]. https://www.iso.org/standard/90322.html.

[32]	Lin JC, Jain B, Iyer JM, Rola I, Srinivasan AR, Kang C, et al. Benefit-risk reporting for FDA-cleared artificial intelligence-enabled medical devices. JAMA Health Forum 2025; 6(9): e253351.

[33]	European Animal Research Association Team. When will animals be replaced in research? EARA feature [Internet]. London: European Animal Research Association Team; [cited 2025 Aug 23]. Available from: https://www.eara.eu/news/when-will-animals-be-replaced-in-research-eara-feature.

[34]	Hossein-Zadeh NG . Artificial intelligence in veterinary and animal science: applications, challenges, and future prospects. Comput Electron Agric 2025; 235: 235.

[35]	Sardelli L, Campanile M, Boeri L, Donnaloja F, Fanizza F, Perottoni S, et al. A novel on-a-chip system with a 3D-bioinspired gut mucus suitable to investigate bacterial endotoxins dynamics. Mater Today Bio 2023; 24: 100898.

[36]	The European Medicines Agency. Regulatory science research needs, EMA/510633/2024 [Internet]. Amsterdam: The European Medicines Agency; [cited 2025 Jul 12]. Available from: https://www.ema.europa.eu/en/about-us/what-we-do/regulatory-science-research/regulatory-science-research-needs.

[37]	Jean-Louis G, Seixas AA . The value of decentralized clinical trials: inclusion, accessibility, and innovation. Science 2024; 385(6711): eadq4994.

[38]	Jiang Y, Leng Y, Wu Q, Hou Y, Dong X, Zeng C, et al. Understanding the gap between expectations and reality in decentralized clinical trials. NPJ Digit Med 2025; 8(1): 408.

[39]	De Brouwer W, Patel CJ, Manrai AK, Rodriguez-Chavez IR, Shah NR . Empowering clinical research in a decentralized world. NPJ Digit Med 2021; 4(1): 102.

[40]	Bauchner H, Fontanarosa PB . Randomized clinical trials and COVID-19: managing expectations. JAMA 2020; 323(22): 2262-3.

[41]	Underhill C, Sabesan S, Wilson E . Decentralised clinical trials: a game changer for improved access to clinical trials. Lancet Oncol 2024; 25(12): e625.

[42]	Kunkoski E, Saha A, Kam MM . FDA perspective on the importance of digital health technologies in clinical trials. JAMA Health Forum 2025; 6(4): e250165.

[43]	Hegyi P, Garami A, Agusti A, Agyemang C, Anadon A, Balla J, et al.; the Academia Europaea Translational Medicine Working Group. Academia Europaea’s guidelines for the visualization of clinical outcomes. Nat Med 2025; 31(12): 3976-80.

[44]	Lee JJ, Harrell FE Jr, LaVange LM, Spiegelhalter DJ . Embracing Bayesian methods in clinical trials: FDA’s long-awaited draft guidance. JAMA 2026; 335(19): 1664.

[45]	Campbell G, Irony T, Pennello G, Thompson L . Bayesian statistics for medical devices: progress since 2010. Ther Innov Regul Sci 2023; 57(3): 453-63.

[46]	Lu Q, Hsueh YS, Tong W, Zhang Y, Xu J, Qin L . Importance to understand medical device regulations for accelerating clinical translation. J Orthop Translat 2025; 51: 290-7.

[47]	Bishnoi M, Sonker A . Emergency use authorization of medicines: history and ethical dilemma. Perspect Clin Res 2023; 14(2): 49-55.

[48]	Simpson S, Chakrabarti A, Robinson D, Chirgwin K, Lumpkin M. Navigating facilitated regulatory pathways during a disease X pandemic. NPJ Vaccines 2020; 5(1): 101.

[49]	Ghadanian M, Schafheutle E . Comparison between European Medicines Agency and US Food and Drug Administration in granting accelerated marketing authorizations for COVID-19 medicines and their utilized regulations. Ther Innov Regul Sci 2024; 58(1): 79-113.

[50]	Simpson C, Gillis AM . The pacemaker and implantable cardioverter defibrillator recall issue-Canadian perspective. Can J Cardiol 2006; 22(6): 467-71.

[51]	Colasacco CJ, Born HL . A case of artificial intelligence chatbot hallucination. JAMA Otolaryngol Head Neck Surg 2024; 150(6): 457-8.

[52]	Khera R, Simon MA, Ross JS . Automation bias and assistive AI: risk of harm from AI-driven clinical decision support. JAMA 2023; 330(23): 2255-7.

[53]

US Food and Drug Administration. Digital Health Software Precertification (Pre-Cert) Pilot Program [Internet]. Silver Spring: US Food and Drug Administration; [cited 2025 Aug 19]. Available from: https://www.fda.gov/medical-devices/digital-health-center-excellence/digital-health-software-precertification-pre-cert-pilot-program.

[54]	Brewer T, Colditz GA . Postmarketing surveillance and adverse drug reactions: current perspectives and future needs. JAMA 1999; 281(9): 824-9.

[55]	Matheny ME, Yang J, Smith JC, Walsh CG, Al-Garadi MA, Davis SE, et al. Enhancing postmarketing surveillance of medical products with large language models. JAMA Netw Open 2024; 7(8): e2428276.

[56]	World Health Organization. Ethics and governance of artificial intelligence for health [Internet]. Geneva: World Health Organization [cited 2026 Jul 1]. Available from: https://www.who.int/publications/i/item/9789240029200.

[57]	Broojerdi AK, Salvati AL, Abdelfattah MR, Dehaghi ROA, Sillo HB, Gaspar R . WHO-listed authorities (WLA) framework: transparent evidence-based approach for promoting regulatory reliance towards increased access to quality-assured medical products. Front Med 2024; 11: 1467229.

[58]	Korteling JEH, van de Boer-Visschedijk GC, Blankendaal RAM, Boonekamp RC, Eikelboom AR . Human versus artificial intelligence. Front Artif Intell 2021; 4: 622364.

[59]	Vaccaro M, Almaatouq A, Malone T . When combinations of humans and AI are useful: a systematic review and meta-analysis. Nat Hum Behav 2024; 8(12): 2293-303.

[60]

The International Medical Device Regulators Forum (IMDRF). Good machine learning practice for medical device development: guiding principles (IMDRF/AIML WG/N88 FINAL:2025) [Internet]. The International Medical Device Regulators Forum; [cited 2026 Aug 17]. Available from: https://www.imdrf.org/documents/good-machine-learning-practice-medical-device-development-guiding-principles.

[61]

US Food and Drug Administration. Predetermined change control plans for machine learning-enabled medical devices: guiding principles [Internet]. Silver Spring: US Food and Drug Administration; [cited 2026 Jul 15]. Available from: https://www.fda.gov/medical-devices/software-medical-device-samd/predetermined-change-control-plans-machine-learning-enabled-medical-devices-guiding-principles.

[62]	Makary MA, Prasad V . Priorities for a new FDA. JAMA 2025; 334(7): 565-6.

[63]	Mathias R, Schmitt A, Campos M, Vasey B, Lorenz S, McCulloch P, et al. Evaluation of human factors-related risks in AI-enabled medical devices-a practical guide. NEJM AI 2026; 3(4): 3.

[64]	Longo L, Brcic M, Cabitza F, Choi J, Confalonieri R, Ser JD, et al. Explainable artificial intelligence (XAI) 2.0: a manifesto of open challenges and interdisciplinary research directions. Inf Fusion 2024; 106: 106.

PDF (6039KB)

0

Accesses

0

Citation

Detail

Sections

Recommended

/

〈

〉