Volume 2 Issue 1 | 2025 | View PDF
Paper Id:IJMSM-V2I1P109
doi: 10.71141/30485037/V2I1P109

Gen AI-Driven Adaptive Clinical Decision Support (GDA-CDSS): Enhancing Patient Outcomes with LLaMA-3 and Federated Learning

Srinivasan Ramalingam, Srinivas Bangalore Sujayendra Rao, Muthuraman Saminathan

Citation:
Srinivasan Ramalingam, Srinivas Bangalore Sujayendra Rao, Muthuraman Saminathan, "Gen AI-Driven Adaptive Clinical Decision Support (GDA-CDSS): Enhancing Patient Outcomes with LLaMA-3 and Federated Learning" International Journal of Multidisciplinary on Science and Management, Vol. 2, No. 1, pp. 84-93, 2025.

Abstract:
The exponential growth of healthcare data, spanning electronic health records (EHRs), wearable sensors and medical imaging demands a paradigm shift in clinical decision-making. Traditional CDSS, based on rigid rule framework, fail to process unstructured data and cannot adapt well to evolution of medical scenarios. This review explores the transformative potential of GDA-CDSS by combining LLaMA-3, a cutting-edge large language model, with Federated Learning (FL) to enable precision medicine while ensuring data privacy. Unlike conventional CDSS which rely on predefined rules, GDA-CDSS dynamically learns from vast and diverse datasets to give real time recommendations tailored to the context. Furthermore, LLaMA-3 enables deep natural language understanding, improves diagnostic accuracy, generates synthetic patient cases while efficiently processing complex clinical narratives. At the same time, FL ensures that such collaboration between hospitals remains privacy preserving, enabling models to be trained on distributed data without revealing the sensitive patient information while meeting the regulations of HIPAA and GDPR. Although, model interpretability, interoperability and bias mitigation are challenges that would need to be overcome for adoption to be widespread. Explainability for LLaMA-3 and FL leads to transparent, trustable recommendations for clinicians and an equitable model training on diverse populations for scalability and interoperability for easy integration with modern healthcare. GDA-CDSS strives to establish LLaMA-3’s lightweight architecture and FL’s decentralized approach for the future of AI powered healthcare for adaptive, intelligent and ethically robust.

Keywords: Federated Learning; LLaMA-3; Healthcare Data; Electronic Health Records (EHR); Adaptive Clinical Decision Support; HIPAA; Compliance.

References:
1. BC Capital Markets, "Navigating the changing face of healthcare episode," accessed Dec. 30, 2024. [Online]. Available: https://www.rbccm.com/en/gib/healthcare/story.page.
2. C. Doherty, M. Baldwin, A. Keogh, et al., "Keeping pace with wearables: a living umbrella review of systematic reviews evaluating the accuracy of consumer wearable technologies in health measurement," Sports Med., vol. 54, no. 11, pp. 2907-2926, 2024, doi: 10.1007/s40279-024-02077-2.
3. K. Anyaso and V. Okoye, "The impact of big data and predictive analytics on U.S. healthcare delivery: opportunities, challenges, and future directions," World J. Adv. Res. Rev., vol. 24, no. 1, pp. 2275-2287, 2024, doi: 10.30574/wjarr.2024.24.1.3266.
4. N. E. Ingraham, E. K. Jones, S. King, J. Dries, M. Phillips, T. Loftus, H. L. Evans, G. B. Melton, and C. J. Tignanelli, "Re-aiming equity evaluation in clinical decision support: a scoping review of equity assessments in surgical decision support systems," Ann. Surg., vol. 277, no. 3, pp. 359-364, 2023.
5. P.-Y. Meunier, C. Raynaud, E. Guimaraes, F. Gueyfer, and L. Letrilliart, "Barriers and facilitators to the use of clinical decision support systems in primary care: A mixed-methods systematic review," Ann. Fam. Med., vol. 21, no. 1, pp. 57-69, 2023.
6. Q. Xu, W. Xie, B. Liao, C. Hu, L. Qin, Z. Yang, H. Xiong, Y. Lyu, Y. Zhou, A. Luo, et al., "Interpretability of clinical decision support systems based on artificial intelligence from technological and medical perspectives: A systematic review," J. Healthcare Eng., vol. 2023, Article 9919269, 2023, doi: 10.1155/2023/9919269.
7. J. Ferdush, M. Begum, and S. T. Hossain, "ChatGPT and clinical decision support: scope, application, and limitations," Ann. Biomed. Eng., vol. 52, pp. 1119-1124, 2024, doi: 10.1007/s10439-023-03329-4.
8. X. Parra, X. Tort-Martorell, F. Alvarez-Gomez, and C. Ruiz-Viñals, "Chronological evolution of the information-driven decision-making process (1950–2020)," Elsevier, vol. 14, pp. 2363-2394, Mar. 2022.
9. P. Papadopoulos, M. Sofano, Y. Chaudy, W. Adejo, and T. M. Connolly, "A systematic review of technologies and standards used in the development of rule-based clinical decision support systems," J. Med. Syst., vol. 46, no. 8, p. 79, 2022.
10. J. P. Shim, M. Warkentin, J. F. Courtney, D. J. Power, R. Sharda, and C. Carlsson, "Past, present, and future of decision support technology," Decis. Support Syst., vol. 33, no. 2, pp. 111-126, Jun. 2002.
11. E. S. Berner and E. S. Lande, "Overview of clinical decision support systems," in Clinical Decision Support Systems, Springer, 2016, pp. 1-17.
12. S. Ramgopal, L. N. Sanchez-Pinto, C. M. Horvat, M. S. Carroll, Y. Luo, and T. A. Florin, "Artificial intelligence-based clinical decision support in pediatrics," Pediatr. Res., vol. 92, no. 3, pp. 467-478, Jul. 2022, doi: 10.1038/s41390-022-02226-1.
13. M. Khalifa, M. Albadawy, and U. Iqbal, "Advancing clinical decision support: The role of artificial intelligence across six domains," Comput. Methods Programs Biomed. Update, vol. 5, p. 100142, Feb. 2024, doi: 10.1016/j.cmpbup.2024.100142.
14. C. A. Gomez-Cabello, S. Borna, S. Pressman, S. A. Haider, C. R. Haider, and A. J. Forte, "Artificial-intelligence-based clinical decision support systems in primary care: A scoping review of current clinical implementations," Eur. J. Investig. Health Psychol. Educ., vol. 14, no. 3, p. 45, Mar. 2024, doi: 10.3390/ejihpe14030045.
15. S. S. Sengar, A. B. Hasan, S. Kumar, and F. Carroll, "Generative artificial intelligence: A systematic review and applications," Multimed. Tools Appl., vol. 83, Aug. 2024, doi: 10.1007/s11042-024-16987-1.
16. H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozière, N. Goyal, E. Hambro, F. Azhar, A. Rodriguez, A. Joulin, E. Grave, and G. Lample, "LLaMA: Open and efficient foundation language models," arXiv preprint, arXiv:2302.13971, 2023. [Online].Available: https://doi.org/10.48550/arXiv.2302.13971.
17. A. Grattafiori et al., "The Llama 3 Herd of Models," arXiv preprint, arXiv:2405.14772, 2024. [Online]. Available: https://arxiv.org/abs/2405.14772.
18. J. Liang, Z. Wang, Z. Ma, J. Li, Z. Zhang, X. Wu, B. Wang, "Online Training of Large Language Models: Learn while chatting," arXiv preprint, arXiv:2403.04790, 2024.
19. T. Che, J. Liu, Y. Zhou, J. Ren, J. Zhou, V. S. Sheng, H. Dai, D. Dou, "Federated learning of large language models with parameter-efficient prompt tuning and adaptive optimization," arXiv preprint, arXiv:2310.15080, 2023.
20. B. Li, L. Fan, H. Gu, J. Li, and Q. Yang, "FedIPR: Ownership verification for federated deep neural network models," IEEE Trans. Pattern Anal. Mach. Intell., 2022.
21. K. Cheng, T. Fan, Y. Jin, Y. Liu, T. Chen, D. Papadopoulos, and Q. Yang, "SecureBoost: A lossless federated learning framework," IEEE Intelligent Systems, vol. 36, no. 6, pp. 87-98, 2021.
22. M. Alkaeed, S. Abioye, A. Qayyum, Y. M. Mekki, I. Berrou, M. Abdallah, A. Al-Fuqaha, M. Bilal, and J. Qadir, "Open foundation models in healthcare: Challenges, paradoxes, and opportunities with GenAI-driven personalized prescription," Proc. IEEE, 2024.
23. S. Volkmer, A. Meyer-Lindenberg, and E. Schwarz, "Large language models in psychiatry: Opportunities and challenges," Psychiatry Research, vol. 339, p. 116026, Sep. 2024.
24. T. Fan, Y. Kang, G. Ma, W. Chen, W. Wei, L. Fan, and Q. Yang, "FATE-LLM: An industrial-grade federated learning framework for large language models," Oct. 16, 2023.
25. Standing Committee of the National People's Congress, "Cybersecurity Law of the People's Republic of China," Jul. 11, 2016. [Online]. Available: http://www.lawinfochina.com/Display.aspx?LookType=3&Lib=law&Id=22826&SearchKeyword=&SearchCKeyword=&paycode=. [Accessed: Feb. 18, 2022].
26. Centers for Disease Control and Prevention, "Health Insurance Portability and Accountability Act of 1996 (HIPAA)," [Online]. Available: https://www.cdc.gov/phlp/publications/topic/hipaa.html. [Accessed: Feb. 18, 2022].
27. California Legislative Information, "Codes Display Text," [Online]. Available: https://leginfo.legislature.ca.gov/faces/codes_displayText.xhtml?division=3.&part=4.&lawCode=CIV&title=1.81.5. [Accessed: Feb. 18, 2022].
28. The Ministry of Justice, "Personal Data Protection Act," [Online]. Available:https://law.moj.gov.tw/ENG/LawClass/LawAll.aspx?pcode=I0050021. [Accessed: Dec. 15, 2012].
29. G. Feretzakis and V. S. Verykios, "Trustworthy AI: Securing sensitive data in large language models," Preprint, Sep. 2024. [Online]. Accessed: Mar. 13, 2025.
30. C. Wang, S. Liu, H. Yang, J. Guo, Y. Wu, and J. Liu, "Ethical considerations of using ChatGPT in health care," J. Med. Internet Res., vol. 25, p. e48009, 2023
31. H. Ali, J. Qadir, T. Alam, M. Househ, and Z. Shah, "ChatGPT and Large Language Models (LLMs) in Healthcare: Opportunities and Risks," in Proc. ChatGPT and Large Language Models (LLMs) in Healthcare, Mount Pleasant, MI, USA, Sep. 16-17, 2023.
32. S. Thapa and S. Adhikari, "ChatGPT, Bard, and Large Language Models for Biomedical Research: Opportunities and Pitfalls," Ann. Biomed. Eng., vol.51,pp. 2647-2651, 2023.
33. R. Daruvuri, K. Patibandla, and P. Mannem, "Leveraging unsupervised learning for workload balancing and resource utilization in cloud architectures," International Research Journal of Modernization in Engineering Technology and Science, vol. 6, no. 10, pp. 1776-1784, 2024.