Multi-Agent AI Systems in Healthcare: Systematic Evidence Synthesis Via PRISMA of Clinical Decision Support Systems, Robotic Interventions, and Critical Care

Abstract: Multi-agent artificial intelligence systems (MAS) is transforming the healthcare sector by enabling intelligent decision-making, robotic interventions, and critical care management. Despite growing interest, a comprehensive synthesis of their real-world applications, performance, and limitations is lacking. This systematic review aims to evaluate the deployment of MAS in healthcare across three key domains: Clinical Decision Support Systems (CDSS), Robotic Interventions, and Critical Care Monitoring. It also addresses ethical and legal considerations, offers a comparative framework, and identifies research gaps. A systematic search of PubMed, IEEE Xplore, Scopus, and Web of Science was conducted following PRISMA guidelines. A total of 150 records were retrieved. After duplicate removal and screening, 32 studies met inclusion criteria. The Joanna Briggs Institute (JBI) Critical Appraisal Checklist guided quality assessment. Data were extracted using a structured form and organized by topic. Among the 32 studies included, 12 focused on MAS-based CDSS, 11 on robotic interventions, and 9 on MAS in critical care. Most MAS demonstrated improved diagnostic accuracy, aided real-time decision support, and enhanced patient monitoring. However, over 60% involved practical models and lacked clinical validation. Ethical concerns, particularly around autonomy, data privacy, transparency, and legal accountability were sometimes overlooked. Only 7 studies discussed ethical or legal implications in depth. A comparative framework was developed, comparing MAS tools based on scalability, clinical validation, autonomy, human-AI interaction, and data transparency. No doubt, MAS hold transformative potential across healthcare domains. However, real-world deployment remains unclear. Greater emphasis on clinical validation, ethical design, and regulatory frameworks is needed. This review provides suggestions for future research and responsible adoption of MAS in healthcare.

Multi-agent systems, artificial intelligence, healthcare robotics, critical care, clinical decision support systems, ethics, legal framework, PRISMA, cc.

1. Durfee EH, Rosenschein JS. Distributed problem solving and multi-agent systems: Comparisons and examples. In: Proceedings of the 13th International Distributed Artificial Intelligence Workshop. 1994 Jul;94–104. [Google Scholar] [Crossref]

2. Kinny D, Georgeff M. Modelling and design of multi-agent systems. In: Müller JP, Wooldridge MJ, Jennings NR, editors. Intelligent Agents III Agent Theories, Architectures, and Languages. ATAL 1996. Lecture Notes in Computer Science, vol 1193. Springer; 1997. p. 56–70. doi:10.1007/BFb0013569. [Google Scholar] [Crossref]

3. Ribino P, Islam S, Ciampi M, Papastergiou S. Swarm intelligence based multi-agent communication model for securing healthcare ecosystem. In: International Conference on Ubiquitous Computing and Ambient Intelligence. Cham: Springer; 2022 Nov. p. 50–61. doi:10.1007/978-3-031-21333-5_5. [Google Scholar] [Crossref]

4. Ahmed MI, Spooner B, Isherwood J, Lane M, Orrock E, Dennison A. A systematic review of the barriers to the implementation of artificial intelligence in healthcare. Cureus. 2023 Oct 4;15(10):e46454. doi:10.7759/cureus.46454. [Google Scholar] [Crossref]

5. Li F, Ruijs N, Lu Y. Ethics & AI: A systematic review on ethical concerns and related strategies for designing with AI in healthcare. AI. 2022;4(1):28–53. [Google Scholar] [Crossref]

6. PRISMA. PRISMA 2020 flow diagram [Internet]. Ottawa: PRISMA; 2020 [cited 2025 Mar 31]. Available from: https://www.prisma-statement.org/prisma-2020-flow-diagram [Google Scholar] [Crossref]

7. Santos WMD, Secoli SR, Püschel VADA. The Joanna Briggs Institute approach for systematic reviews. Rev Lat Am Enfermagem. 2018;26:e3074. doi:10.1590/1518-8345.2885.3074. [Google Scholar] [Crossref]

8. Ghezloo F, Seyfioğlu MS, Soraki R, Ikezogwo W, Li B, Vivekanandan T, et al. PathFinder: A Multi-Modal Multi-Agent System for Medical Diagnostic Decision-Making Applied to Histopathology [preprint]. 2025 Feb. Available from: https://arxiv.org/abs/2502.08916 [Google Scholar] [Crossref]

9. Chen YJ, Chen CS, Albarqawi A. Reinforcing clinical decision support through multi-agent systems and ethical AI governance [preprint]. 2025 Mar 25. Available from: https://arxiv.org/abs/2504.03699 [Google Scholar] [Crossref]

10. Aydin Y, Tokatli O, Patoglu V, Basdogan C. A computational multicriteria optimization approach to controller design for physical human-robot interaction. IEEE Trans Robot. 2020 Dec;36(6):1791–804. doi:10.1109/TRO.2020.2998606. [Google Scholar] [Crossref]

11. Karami V, Yaffe MJ, Gore G, Moon AJ, Rahimi SA. Socially assistive robots for patients with Alzheimer's disease: A scoping review. Arch Gerontol Geriatr. 2024;105409. doi:10.1016/j.archger.2024.105409. [Google Scholar] [Crossref]

12. Cho A, Woo JM, Shi B, Udeshi A, Woo JSH. The application of MATEC (Multi-AI Agent Team Care) framework in sepsis care [preprint]. 2025 Feb 9. Available from: https://arxiv.org/abs/2503.16433 [Google Scholar] [Crossref]

13. Li B, Yue L, Nie H, Cao Z, Chai X, Peng B, et al. The effect of intelligent management interventions in intensive care units to reduce false alarms: An integrative review. Int J Nurs Sci. 2023 Dec 14;11(1):133–42. doi:10.1016/j.ijnss.2023.12.008. [Google Scholar] [Crossref]

14. European Parliament. Artificial Intelligence Act: MEPs adopt landmark law [Internet]. 2024 Mar 8 [cited 2025 Jun 10]. Available from: https://www.europarl.europa.eu/news/en/press-room/20240308IPR19015/artificial-intelligence-act-meps-adopt-landmark-law [Google Scholar] [Crossref]

15. Mienye ID, Obaido G, Jere N, Mienye E, Aruleba K, Emmanuel ID, Ogbuokiri B. A survey of explainable artificial intelligence in healthcare: Concepts, applications, and challenges. Inform Med Unlocked. 2024;51:101587. doi:10.1016/j.imu.2024.101587. [Google Scholar] [Crossref]

16. Sharma RK. Enabling scalable and secure healthcare data analytics with cloud-native AI architectures. Technology (IJRCAIT). 2025;8(1). [Google Scholar] [Crossref]

17. Shapiro MA, Stuhlmiller TJ, Wasserman A, Kramer GA, Federowicz B, Hoos W, et al. AI-augmented clinical decision support in a patient-centric precision oncology registry. AI Precision Oncol. 2024;1(1):58–68. [Google Scholar] [Crossref]

18. Nimri R, Phillip M. Enhancing care in type 1 diabetes with artificial intelligence driven clinical decision support systems. Horm Res Paediatr. 2025. [Google Scholar] [Crossref]

19. Ying Z, Fan Y, Chen C, Liu Y, Tang Q, Chen Z, Chen Y. Real-time AI-assisted insulin titration system for glucose control in patients with type 2 diabetes: A randomized clinical trial. JAMA Netw Open. 2025 May;8(5):e258910. doi:10.1001/jamanetworkopen.2025.8910. [Google Scholar] [Crossref]

20. Jiménez AC, García-Díaz V, Bolaños S. A decentralized framework for multi-agent robotic systems. Sensors. 2018 Feb;18(2):417. doi:10.3390/s18020417. [Google Scholar] [Crossref]

21. Gurusamy KS, Samraj K, Fusai G, Davidson BR. Robot assistant for laparoscopic cholecystectomy. Cochrane Database Syst Rev. 2009;(1):CD006578. doi:10.1002/14651858.CD006578.pub2. [Google Scholar] [Crossref]

22. Rodrigues R, Gonc P, Miranda M, Portela F, Santos M, Neves J, et al. Monitoring intelligent system for the intensive care unit using RFID and multi-agent systems. In: IEEE International Conference on Industrial Engineering and Engineering Management; 2012 Dec 10. p. 851–5. [Google Scholar] [Crossref]

23. Malak JS, Zeraati H, Nayeri FS, Safdari R, Shahraki AD. Neonatal intensive care decision support systems using artificial intelligence techniques: A systematic review. Artif Intell Rev. 2019 Dec;52:2685–704. [Google Scholar] [Crossref]

24. Picelli A, Melotti C, Origano F, Waldner A, Fiaschi A, Santilli V, et al. Robot-assisted gait training in patients with Parkinson disease: A randomized controlled trial. Neurorehabil Neural Repair. 2012 May;26(4):353–61. doi:10.1177/1545968311424417. [Google Scholar] [Crossref]

25. Castelli Gattinara Di Zubiena F, Menna G, Mileti I, Zampogna A, Asci F, Paoloni M, et al. Machine learning and wearable sensors for the early detection of balance disorders in Parkinson’s disease. Sensors. 2022 Dec 16;22(24):9903. [Google Scholar] [Crossref]

26. Rodriguez F, Krauss P, Kluckert J, Ryser F, Stieglitz L, Baumann C, et al. Continuous and unconstrained tremor monitoring in Parkinson’s disease using supervised machine learning and wearable sensors. Parkinsons Dis. 2024;2024:5787563. [Google Scholar] [Crossref]

27. World Health Organization. Ethics and governance of artificial intelligence for health: WHO guidance. Geneva: WHO; 2021. ISBN 978-92-4-002920-0 (electronic), 978-92-4-002921-7 (print). Available from: https://creativecommons.org/licenses/by-nc-sa/3.0/igo [Google Scholar] [Crossref]

28. Fosch Villaronga E, Khanna P, Drukarch HG, Custers B. A human in the loop in surgery automation. Nat Mach Intell. 2021 May;3(5):1–2. doi:10.1038/s42256-021-00349-4. [Google Scholar] [Crossref]

29. Pati S, Kumar S, Varma A, Edwards B, Lu C, Qu L, et al. Privacy preservation for federated learning in health care. Patterns (N Y). 2024;5(3):100974. doi:10.1016/j.patter.2024.100974. [Google Scholar] [Crossref]

30. Solanki P, Grundy J, Hussain W. Operationalising ethics in artificial intelligence for healthcare: A framework for AI developers. AI Ethics. 2023;3:223–40. doi:10.1007/s43681-022-00195-z. [Google Scholar] [Crossref]

31. Saarela M, Podgorelec V. Recent applications of explainable AI (XAI): A systematic literature review. Appl Sci. 2024;14(19):8884. doi:10.3390/app14198884. [Google Scholar] [Crossref]

32. Fraser AG, Biasin E, Bijnens B, Bruining N, Caiani EG, Cobbaert K, et al. Artificial intelligence in medical device software and high-risk medical devices – a review of definitions, expert recommendations and regulatory initiatives. Expert Rev Med Devices. 2023;20(6):467–91. doi:10.1080/17434440.2023.2184685. [Google Scholar] [Crossref]

33. Romero-Brufau S, Whitford D, Johnson MG, Hickman J, Morlan BW, Therneau T, et al. Using machine learning to improve the accuracy of patient deterioration predictions: Mayo Clinic Early Warning Score (MC-EWS). J Am Med Inform Assoc. 2021 Jun 1;28(6):1207–15. [Google Scholar] [Crossref]

34. Romero-Brufau S, Whitford D, Johnson MG, Hickman J, Morlan BW, Therneau T, et al. Using machine learning to improve the accuracy of patient deterioration predictions: Mayo Clinic Early Warning Score (MC-EWS). J Am Med Inform Assoc. 2021 Jun 1;28(6):1207–15. doi:10.1093/jamia/ocab012. [Google Scholar] [Crossref]

35. Wong A, Cao J, Lyons PG, Dutta S, Major VJ, Otles E, Singh K. Quantification of sepsis model alerts in 24 US hospitals before and during the COVID-19 pandemic. JAMA Netw Open. 2021 Nov 1;4(11):e2135286. [Google Scholar] [Crossref]

36. Slack G. A better, faster sepsis test that can save lives. Innovation & Technology. 2025 Feb 5. Available from: https://med.stanford.edu/news/insights/2025/02/sepsis-infection-new-test-genetic.html [Google Scholar] [Crossref]

37. Gobinath A, Rajeswari P, Suresh KN, Anandan M. Robotics in real-time applications in healthcare systems. In: AI and IoT Technology and Applications for Smart Healthcare Systems. Auerbach Publications; 2024 May 15. p. 262–74. [Google Scholar] [Crossref]

38. Hospital Management Asia. AI-powered patient monitoring system at Apollo Hospitals cut Code Blues by 80%. 2025 Feb 6. Available from: https://www.hospitalmanagementasia.com/patient-safety/ai-powered-patient-monitoring-system-at-apollo-hospitals-cut-code-blues-by-80/ [Google Scholar] [Crossref]

39. Verlingue L, Boyer C, Olgiati L, Brutti M, Morel D, Blay JY. Artificial intelligence in oncology: ensuring safe and effective integration of language models in clinical practice. [Internet]. 2024 Nov [cited 2025 Jun 10]. Available from: [Publisher link unavailable]. [Google Scholar] [Crossref]

40. He J, Baxter SL, Xu J, Zhou X, Zhang K. The practical implementation of artificial intelligence technologies in medicine. Nat Med. 2019 Jan;25(1):30–6. [Google Scholar] [Crossref]

41. Morley J, Machado CC, Burr C, Cowls J, Joshi I, Taddeo M, Floridi L. The ethics of AI in health care: A mapping review. Soc Sci Med. 2020;260:113172. [Google Scholar] [Crossref]

• Wind Turbine Design for Low Wind Speed Applications: Advancing Renewable Energy Systems Through Wind Tunnel Experiments
• Fast Identification for Evidences in Crime Scene with Macroscopic Properties and Portable Techniques
• Evaluating the Impact of Hello Interval Timer on OSPF Performance for Real-Time Applications Using OPNET
• The Algorithmic Fortress: Ai-Powered Cybersecurity and Anti-Fraud in The Future of Fintech
• Accident Detection on Curved Roads Using Infrared Sensors in Hilly Regions A Case of Chadoora Tehsil, Badgam (J&K)