Investigating the Use of Federated Learning for Diabetes Detection and Management

• Lucas S. de Oliveira UFSC
• Alison R. Panisson UFSC
• Jim Lau UFSC
• Iwens G. Sene UFG
• Analucia Schiaffino Morales UFSC

DOI: https://doi.org/10.5753/sbcas.2025.6956

Abstract

This study explores federated learning for diabetes detection and monitoring using physiological data from wearable-like devices. A server and two ESP32 devices form the system, aiming to enhance early diagnosis and personalized care. Three datasets—Ohio T1DM, DiaHealth, and GBS—were processed with dimensionality reduction, outlier removal, and balancing techniques. Key biomarkers include glycemic index, heart rate, temperature, sweat, and oxygen saturation. Machine learning models were trained in Orange Data Mining and evaluated via precision, recall, F1-score, and accuracy. Random Forest excelled as the global model within the federated framework, with local customization on ESP32 despite memory constraints. Federated learning proves promising for personalized diabetes monitoring, with future improvements suggested through daily activity data integration.

Keywords: Federated Learning, Diabetes

References

Ara, A. and Ara, A. (2017). Case study: Integrating iot, streaming analytics and machine learning to improve intelligent diabetes management system. In 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), pages 3179–3182.

Awoniran, O., Oyelami, M., Ikono, R., Famutimi, R., and Famutimi, T. (2022). A machine learning technique for detection of diabetes mellitus. In 2022 5th Information Technology for Education and Development (ITED), pages 1–6. IEEE.

Barakat, N., Bradley, A. P., and Barakat, M. N. H. (2010). Intelligible support vector machines for diagnosis of diabetes mellitus. IEEE transactions on information technology in biomedicine, 14(4):1114–1120.

Biessels, G. J., Staekenborg, S., Brunner, E., Brayne, C., and Scheltens, P. (2006). Risk of dementia in diabetes mellitus: a systematic review. The Lancet Neurology, 5(1):64–74.

Butt, M. D., Ong, S. C., Rafiq, A., Kalam, M. N., Sajjad, A., Abdullah, M., Malik, T., Yaseen, F., and Babar, Z.-U.-D. (2024). A systematic review of the economic burden of diabetes mellitus: contrasting perspectives from high and low middle-income countries. Journal of pharmaceutical policy and practice, 17(1):2322107.

Dhade, P. and Shirke, P. (2024). Federated learning for healthcare: A comprehensive review. Engineering Proceedings, 59(1):230.

El Jerjawi, N. S. and Abu-Naser, S. S. (2018). Diabetes prediction using artificial neural network.

Ghozali, M. T. (2024). Improving self-management of type 2 diabetes: Evaluating the effectiveness of a mobile app-based patient education approach. In 2024 4th International Conference on Emerging Smart Technologies and Applications, pages 1–5.

Golledge, J., Fernando, M., Lazzarini, P., Najafi, B., and G. Armstrong, D. (2020). The potential role of sensors, wearables and telehealth in the remote management of diabetes-related foot disease. Sensors, 20(16):4527.

Gross, J. L., Silveiro, S. P., Camargo, J. L., Reichelt, A. J., and Azevedo, M. J. d. (2002). Diabetes melito: diagnóstico, classificação e avaliação do controle glicêmico. Arquivos Brasileiros de Endocrinologia & Metabologia, 46:16–26.

Jabara, M., Kose, O., Perlman, G., Corcos, S., Pelletier, M.-A., Possik, E., Tsoukas, M., and Sharma, A. (2024). Artificial intelligence-based digital biomarkers for type 2 diabetes: A review. Canadian Journal of Cardiology, 40(10):1922–1933. Theme Issue: Rapidly Evolving Clinical Applications of Artificial Intelligence.

Javale, D. and Desai, S. (2021). Dataset for people for their blood glucose level with their superficial body feature readings. IEEE Dataport.

Malta, D. C., Stopa, S. R., Szwarcwald, C. L., Gomes, N. L., Silva Júnior, J. B., and Reis, A. A. C. d. (2015). A vigilância e o monitoramento das principais doenças crônicas não transmissíveis no brasil - pesquisa nacional de saúde, 2013. Revista Brasileira de Epidemiologia, 18:03–16.

Marling, C. and Bunescu, R. (2020). The ohiot1dm dataset for blood glucose level prediction: Update 2020. In CEUR workshop proceedings, volume 2675, page 71.

Mutunhu, B., Chipangura, B., and Twinomurinzi, H. (2022). A systematized literature review: internet of things (iot) in the remote monitoring of diabetes. In Proceedings of Seventh International Congress on Information and Communication Technology: ICICT 2022, London, Volume 2, pages 649–660. Springer.

Mutunhu, B., Chipangura, B., and Twinomurinzi, H. (2023). A systematized literature review: Internet of things (iot) in the remote monitoring of diabetes. In Yang, X.-S., Sherratt, S., Dey, N., and Joshi, A., editors, Proceedings of Seventh International Congress on Information and Communication Technology, pages 649–660.

Nilson, E. A. F., Andrade, R. d. C. S., Brito, D. A. d., and Oliveira, M. L. d. (2020). Custos atribuíveis a obesidade, hipertensão e diabetes no sistema único de saúde, brasil, 2018. Revista Panamericana de Salud Pública, 44:e32.

Oliveira, G. P. M., Amâncio, N. d. F. G., and da Silva, J. L. (2024). A relação dos fatores socioeconômicos no desenvolvimento e tratamento do diabetes mellitus tipo 2. Brazilian Journal of Implantology and Health Sciences, 6(2):1873–1887.

Prama, T. T., Zaman, M., Sarker, F., and Mamun, K. A. (2024). Diahealth: A bangladeshi dataset for type 2 diabetes prediction.

Ramos, H. S., Maia, G., Papa, G. L., Alvim, M. S., Loureiro, A. A., Cardoso-Pereira, I., Campos, D. H., Filipakis, G., Riquetti, G., Chagas, E. T., et al. (2021). Aprendizado federado aplicado à internet das coisas.

Rodacki, M., Cobas, R., Zajdenverg, L., da Silva Júnior, W., Giacaglia, L., Calliari, L., Noronha, R., Valerio, C., Custódio, J., Scharf, M., et al. (2024). Diagnóstico de diabetes mellitus. Diretriz Oficial da Sociedade Brasileira de Diabetes.

Rodriguez-León, C., Villalonga, C., Munoz-Torres, M., Ruiz, J. R., and Banos, O. (2021). Mobile and wearable technology for the monitoring of diabetes-related parameters: Systematic review. JMIR mHealth and uHealth, 9(6):e25138.

Sneha, N. and Gangil, T. (2019). Analysis of diabetes mellitus for early prediction using optimal features selection. Journal of Big data, 6(1):1–19.

Su, Y., Huang, C., Zhu, W., Lyu, X., and Ji, F. (2023). Multi-party diabetes mellitus risk prediction based on secure federated learning. Biomedical Signal Processing and Control, 85:104881.

Upamanyu, M., Chandan, M., Amrutha, H., Veena, K., Upendra, R., and Karthik, R. (2024). Early prediction of type-ii diabetes mellitus in young adults using lstm. In 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), pages 1–6. IEEE.

Xu, Z. and Wang, Z. (2019). A risk prediction model for type 2 diabetes based on weighted feature selection of random forest and xgboost ensemble classifier. In 2019 eleventh international conference on advanced computational intelligence, pages 278–283.

Zhang, C., Xie, Y., Bai, H., Yu, B., Li, W., and Gao, Y. (2021). A survey on federated learning. Knowledge-Based Systems, 216:106775.

Zou, Y., Chu, Z., Yang, T., Guo, J., and Li, D. (2024). Research progress and prospects of intelligent diabetes monitoring systems: a review. IEEE Sensors Journal.