Multi-Agent Large Language Models for Personalized Healthcare Decision Support and Clinical Workflow Automation
Keywords:
multi-agent systems; large language models; clinical decision support; workflow automation; healthcare governance; fairness; interoperability; sociotechnical systemsAbstract
Multi-agent large language models are emerging as a promising architecture for personalized healthcare decision support and clinical workflow automation, yet their integration into care delivery raises structural questions that extend beyond model accuracy. This paper examines the system-level design, governance, deployment, and sustainability implications of multi-agent architectures in clinical environments. It argues that the value of such systems depends less on isolated language model performance than on how agents are coordinated, how clinical knowledge is represented, how human oversight is preserved, and how accountability is distributed across institutions, vendors, clinicians, and patients. The discussion situates multi-agent systems within sociotechnical health informatics, emphasizing interoperability, workflow fit, safety assurance, fairness, and policy alignment. Architectural trade-offs are analyzed across centralized orchestration, federated coordination, and hybrid deployment models, with attention to latency, auditability, resilience, and cost. The paper also considers how personalized decision support can be reconciled with population-level equity, regulatory oversight, and data protection. Special attention is given to the risks of automation bias, opaque delegation among agents, and the erosion of clinical accountability when recommendations are generated through layered model interactions. The analysis concludes that durable adoption requires governance mechanisms that treat multi-agent clinical systems as governed infrastructure rather than standalone software. Such infrastructure must support continuous monitoring, versioned clinical logic, transparent escalation pathways, and participatory evaluation with clinicians, patients, and regulators. The paper contributes a forward-looking systems perspective for researchers, health system leaders, and policymakers seeking to deploy multi-agent language models responsibly in high-stakes care settings.
References
1. Topol, E. J. (2019). Deep medicine: How artificial intelligence can make healthcare human again. Basic Books.
2. Rajkomar, A., Dean, J., & Kohane, I. (2019). Machine learning in medicine. New England Journal of Medicine, 380(14), 1347–1358.
3. Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464), 447–453.
4. Char, D. S., Shah, N. H., & Magnus, D. (2018). Implementing machine learning in health care—Addressing ethical challenges. New England Journal of Medicine, 378(11), 981–983.
5. Sendak, M. P., Gao, M., Brajer, N., & Balu, S. (2020). Presenting machine learning model information to clinical end users with a model facts label. npj Digital Medicine, 3, 42.
6. Amann, J., Blasimme, A., Vayena, E., Frey, D., & Madai, V. I. (2020). Explainability for artificial intelligence in healthcare: A multidisciplinary perspective. BMC Medical Informatics and Decision Making, 20, 310.
7. Gerke, S., Minssen, T., & Cohen, G. (2020). Ethical and legal challenges of artificial intelligence-driven healthcare. Artificial Intelligence in Medicine, 110, 101936.
8. Price, W. N., & Cohen, I. G. (2019). Privacy in the age of medical big data. Nature Medicine, 25(1), 37–43.
9. Sittig, D. F., & Singh, H. (2010). A new sociotechnical model for studying health information technology in complex adaptive healthcare systems. Quality and Safety in Health Care, 19(Suppl 3), i68–i74.
10. Greenhalgh, T., Wherton, J., Papoutsi, C., Lynch, J., Hughes, G., A'Court, C., Hinder, S., Fahy, N., Procter, R., & Shaw, S. (2017). Beyond adoption: A new framework for theorizing and evaluating nonadoption, abandonment, and challenges to the scale-up, spread, and sustainability of health and care technologies. Journal of Medical Internet Research, 19(11), e367.
11. Coiera, E. (2019). The last mile: Where artificial intelligence meets reality. Journal of Medical Internet Research, 21(11), e16323.
12. Cutillo, C. M., Sharma, K. R., Foschini, L., Kundu, S., Mackintosh, M., Mandl, K. D., & MI in Healthcare Workshop Working Group. (2020). Machine intelligence in healthcare—Perspectives on trustworthiness, explainability, usability, and transparency. npj Digital Medicine, 3, 47.
13. Jiang, Hao, et al. "AgentOmnia: Scaling Agentic Models for Full-Scenario Applications." arXiv preprint arXiv:2607.23124 (2026).
14. Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Awadallah, A., White, R. W., Burger, D., & Wang, C. (2023). AutoGen: Enabling next-gen LLM applications via multi-agent conversation. arXiv preprint arXiv:2308.08155.
15. Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023). Generative agents: Interactive simulacra of human behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, 1–22.
16. Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing reasoning and acting in language models. International Conference on Learning Representations.
17. Thirunavukarasu, A. J., Ting, D. S. J., Elangovan, K., Gutierrez, L., Tan, T. F., & Ting, D. S. W. (2023). Large language models in medicine. Nature Medicine, 29(8), 1930–1940.
18. Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., Payne, P., Seneviratne, M., Gamble, P., Kelly, C., Babiker, A., Scharli, N., Chowdhery, A., Mansfield, P., Demner-Fushman, D., ... Natarajan, V. (2023). Large language models encode clinical knowledge. Nature, 620(7972), 172–180.
19. Moor, M., Banerjee, O., Abad, Z. S. H., Krumholz, H. M., Leskovec, J., Topol, E. J., & Rajpurkar, P. (2023). Foundation models for generalist medical artificial intelligence. Nature, 616(7956), 259–265.
20. World Health Organization. (2021). Ethics and governance of artificial intelligence for health: WHO guidance. World Health Organization.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Data Intelligence and AI Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
