Evaluating Open-Source Large Language Models for Educational Applications

Year : 2026 | Volume : 13 | Issue : 02 | Page : 10 21
By

Bhavisha Vishalbhai Parvadiya,

Sahidsha Abdulhamid Diwan,

  1. Assistant Professor, Sardar Patel College of Administration and Management, SPEC campus, Gujarat, India
  2. Student, Sardar Patel College of Administration and Management, SPEC campus, Gujarat, India

Abstract

Mobile healthcare technologies generate sensitive information through electronic health records, smartphones, wearable sensors, medical imaging systems, and remote monitoring platforms. These distributed data sources can improve disease prediction, continuous monitoring, clinical decision support, and personalized healthcare, but centralized collection creates substantial privacy, security, interoperability, and data-governance concerns. Federated learning (FL) provides a distributed machine learning paradigm in which participating healthcare institutions and personal devices collaboratively train models while retaining raw data at their original locations. This paper presents a focused review of FL for privacy-preserving mobile healthcare, emphasizing system architecture, learning mechanisms, healthcare applications, privacy protection, security threats, and deployment challenges. The discussion covers electronic health records, medical imaging, wearable sensing, remote patient monitoring, and multimodal healthcare. Federated Averaging (FedAvg), differential privacy, secure aggregation, homomorphic encryption, and trusted execution environments are examined as important components of privacy-aware FL systems. Recent research from 2024–2026 indicates a shift from proof-of-concept experiments toward multimodal learning, resource-aware architectures, secure Internet of Medical Things (IoMT) integration, and clinically oriented evaluation. The review also identifies persistent limitations involving non-IID data, device heterogeneity, communication overhead, model poisoning, privacy leakage, interoperability, fairness, explainability, and clinical validation. Based on these observations, the paper outlines research directions centered on adaptive aggregation, efficient edge training, personalized models, multimodal federation, robust security, standardized evaluation, and real-world clinical deployment.

Keywords: Federated learning, mobile healthcare, privacy preservation, Internet of Medical Things, wearable devices, electronic health records, secure aggregation, differential privacy, medical imaging

[This article belongs to Journal of Open Source Developments ]

How to cite this article: Bhavisha Vishalbhai Parvadiya, Sahidsha Abdulhamid Diwan. Evaluating Open-Source Large Language Models for Educational Applications. Journal of Open Source Developments. 2026; 13(02):10-21.
How to cite this URL: Bhavisha Vishalbhai Parvadiya, Sahidsha Abdulhamid Diwan. Evaluating Open-Source Large Language Models for Educational Applications. Journal of Open Source Developments. 2026; 13(02):10-21. Available from: https://journals.stmjournals.com/joosd/article=2026/view=260004

References

  1. Rieke N, Hancox J, Li W, Milletarì F, Roth HR, Albarqouni S, et al. The future of digital health with federated learning. NPJ Digit Med. 2020;3(1):119. doi:10.1038/s41746-020-00323-1. PMID:33015372.
  2. McMahan B, Moore E, Ramage D, Hampson S, Aguera y Arcas BA. Communication-efficient learning of deep networks from decentralized data. 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, FL, USA. 2017. p.1273–82.
  3. Teo ZL, Jin L, Li S, Miao D, Zhang X, Ng WY, et al. Federated machine learning in healthcare: a systematic review on clinical applications and technical architecture. Cell Rep Med. 2024;5(2):101419. doi:10.1016/j.xcrm.2024.101419. PMID:38340728.
  4. Abbas SR, Abbas Z, Zahir A, Lee SW. Federated learning in smart healthcare: a comprehensive review on privacy, security, and predictive analytics with IoT integration. Healthcare (Basel). 2024;12(24):2587. doi:10.3390/healthcare12242587. PMID:39766014.
  5. Kanauzia R, Singh M, Gulati S, Singh BM, Arora N, Gola KK. A comprehensive survey on federated learning for privacy preservation in digital healthcare applications. Knowl Inf Syst. 2026;68:55. doi:10.1007/s10115-025-02673-2.
  6. Ghosh D, Mehjabin M, Rayed ME, Mridha MF, Kabir MM. Advancements and challenges of federated learning in medical imaging: a systematic literature review. Artif Intell Rev. 2026;59(2):87. doi:10.1007/s10462-025-11489-z.
  7. Guan H, Yap PT, Bozoki A, Liu M. Federated learning for medical image analysis: a survey. Pattern Recognit. 2024;151:110424. doi:10.1016/j.patcog.2024.110424. PMID:38559674.
  8. Nemane S, Sarad VM, Tulaskar P, Marode TP, Bhangdiya V, Agrawal L, et al. Federated learning in multimodal healthcare diagnostics: privacy-preserving AI for biomedical imaging, electronic health records, wearables, and clinical decision support. Arch Comput Methods Eng. 2026:1–34. doi:10.1007/s11831-026-10629-0.
  9. Nguyen DC, Pham QV, Pathirana PN, Ding M, Seneviratne A, Lin Z, et al. Federated learning for smart healthcare: a survey. ACM Comput Surv. 2022;55(3):1–37. doi:10.1145/3501296.
  10. Kumar KAS, Nelson L, Jibinsingh BR. Systematic review of privacy-preserving federated learning in decentralized healthcare systems. Franklin Open. 2025;13:100440. doi:10.1016/j.fraope.2025.100440.
  11. Lorenzer L, Schrempf M, Jauk S, Kalabakov S, Pierri G, Suzuki KMF, et al. Harmonization of electronic medical records for federated learning: addressing challenges in international healthcare collaborations. Stud Health Technol Inform. 2025;324:141–147. doi:10.3233/SHTI250175. PMID:40270399.
  12. Abadi M, Chu A, Goodfellow IJ, McMahan HB, Mironov I, Talwar K, et al. Deep learning with differential privacy. 23rd ACM SIGSAC Conference on Computer and Communications Security (CCS), Vienna, Austria. 2016. p.308–18. doi:10.1145/2976749.2978318.
  13. Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, et al. Practical secure aggregation for privacy-preserving machine learning. 24th ACM SIGSAC Conference on Computer and Communications Security (CCS), Dallas, TX, USA. 2017. p.1175–91. doi:10.1145/3133956.3133982.
  14. Khan H, Kavati R, Pulkaram SS, Jalooli A. End-to-end privacy-aware federated learning for wearable health devices via encrypted aggregation in programmable networks. Sensors (Basel). 2025;25(22):7023. doi:10.3390/s25227023. PMID:41305229.
  15. Almogadwy B, Alqarafi A. Fused federated learning framework for secure and decentralized patient monitoring in healthcare 5.0 using IoMT. Sci Rep. 2025;15(1):24263. doi:10.1038/s41598-025-06574-w. PMID:40624105.
  16. Kairouz P, McMahan HB. Advances and open problems in federated learning. Found Trends Mach Learn. 2021;14(1-2):1–210. doi:10.1561/2200000083.
  17. Thrasher J, Devkota A, Siwakoti P, Chivukula R, Poudel P, Hu C, et al. Multimodal federated learning in healthcare: a review. J Healthc Inform Res. 2025;10:419–448. doi:10.1007/s41666-025-00226-4.
  18. Raza A, Guzzo A, Ianni M, Lappano R, Zanolini A, Maggiolini M, et al. Federated learning in radiomics: a comprehensive meta-survey on medical image analysis. Comput Methods Programs Biomed. 2025;267:108768. doi:10.1016/j.cmpb.2025.108768. PMID:40279838.
  19. Tanveer F, Iradat F, Iqbal W, Alsagri HS, Alhakbani HAA, Ahmad A, et al. Balancing privacy and performance in healthcare: a federated learning framework for sensitive data. Digit Health. 2025;11:20552076251381769. doi:10.1177/20552076251381769. PMID:41018509.
Regular Issue Subscription Review Article
Volume 13
Issue 02
Received 29/08/2026
Accepted 26/09/2026
Published 28/09/2026
Publication Time 30 Days

Login

My IP

PlumX Metrics

Support