Logo PTI Logo FedCSIS

Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 43

Attention-Based Multi-Task Learning and PPO Reinforcement Learning for Explainable Blood Glucose Prediction

, ,

DOI: http://dx.doi.org/10.15439/2025F2640

Citation: Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 43, pages 333–338 ()

Full text

Abstract. Accurate blood glucose prediction is critical for effective diabetes management, yet existing models struggle with individual variability, data sparsity, and non-linearity. We propose an attention-based multi-task learning (MTL) model integrated with proximal policy optimization (PPO) reinforcement learning (RL) to enhance forecasting accuracy and adaptability. MTL captures shared patterns across multiple prediction tasks, while PPO dynamically refines predictions based on patient-specific glucose trends. By incorporating explainability techniques such as SHAP analysis and Monte Carlo dropout, our approach not only achieves state-of-the-art predictive accuracy but also enhances trust in AI-driven decision support systems for diabetes care. Evaluated on the BrisT1D blood glucose dataset, our model achieves a $R^{2}$ score of 0.85, MSE of 0.0017, RMSE of 0.0419, and MAE of 0.0310, significantly surpassing conventional methods. This work advances personalized real-time glucose forecasting, offering a promising step toward AI-powered glycemic management in clinical settings.

References

  1. P. Aschner, S. Karuranga, S. James, D. Simmons, A. Basit, J. E. Shaw, S. H. Wild, K. Ogurtsova, and P. Saeedi, “The international diabetes federation’s guide for diabetes epidemiological studies,” Diabetes research and clinical practice, vol. 172, 2021.
  2. C. Pihoker, B. H. Braffett, T. J. Songer, W. H. Herman, M. Tung, S. Kuo, A. Bellatorre, E. Isganaitis, E. T. Jensen, J. Divers et al., “Diabetes care barriers, use, and health outcomes in younger adults with type 1 and type 2 diabetes,” JAMA network open, vol. 6, no. 5, pp. e2 312 147–e2 312 147, 2023.
  3. R.-q. Yao, C. Ren, G.-s. Wu, Y.-b. Zhu, Z.-f. Xia, and Y.-m. Yao, “Is intensive glucose control bad for critically ill patients? a systematic review and meta-analysis,” International journal of biological sciences, vol. 16, no. 9, p. 1658, 2020.
  4. T. S. Bailey and S. Alva, “Landscape of continuous glucose monitoring (cgm) and integrated cgm: accuracy considerations,” Diabetes technology & therapeutics, vol. 23, no. S3, pp. S–5, 2021.
  5. J. Yang, L. Li, Y. Shi, and X. Xie, “An arima model with adaptive orders for predicting blood glucose concentrations and hypoglycemia,” IEEE journal of biomedical and health informatics, vol. 23, no. 3, pp. 1251–1260, 2018.
  6. I. Barman, C.-R. Kong, N. C. Dingari, R. R. Dasari, and M. S. Feld, “Development of robust calibration models using support vector machines for spectroscopic monitoring of blood glucose,” Analytical chemistry, vol. 82, no. 23, pp. 9719–9726, 2010.
  7. C. Srichan, W. Srichan, P. Danvirutai, C. Ritsongmuang, A. Sharma, and S. Anutrakulchai, “Non-invasively accuracy enhanced blood glucose sensor using shallow dense neural networks with nir monitoring and medical features,” Scientific Reports, vol. 12, no. 1, p. 1769, 2022.
  8. H. Y. Lu, P. Lu, J. E. Hirst, L. Mackillop, and D. A. Clifton, “A stacked long short-term memory approach for predictive blood glucose monitoring in women with gestational diabetes mellitus,” Sensors, vol. 23, no. 18, p. 7990, 2023.
  9. S.-M. Lee, D.-Y. Kim, and J. Woo, “Glucose transformer: Forecasting glucose level and events of hyperglycemia and hypoglycemia,” IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 3, pp. 1600–1611, 2023.
  10. M. Jaloli and M. Cescon, “Long-term prediction of blood glucose levels in type 1 diabetes using a cnn-lstm-based deep neural network,” Journal of diabetes science and technology, vol. 17, no. 6, pp. 1590–1601, 2023.
  11. S. J. Chu, N. Amarasiri, S. Giri, and P. Kafle, “Blood glucose level prediction in type 1 diabetes using machine learning,” arXiv preprint https://arxiv.org/abs/2502.00065, 2025.
  12. G. Frontino, M. Matarazzo, R. Franceschi, E. Mozzillo, and M. Marigliano, “Diabetes complications in children and adolescents: from low-resource to technology-advanced countries,” p. 1567692, 2025.
  13. P. Domanski, A. Ray, K. Lafata, F. Firouzi, K. Chakrabarty, and D. Pflüger, “Advancing blood glucose prediction with neural architecture search and deep reinforcement learning for type 1 diabetics,” Biocybernetics and Biomedical Engineering, vol. 44, no. 3, pp. 481–500, 2024.
  14. L. Dénes-Fazakas, G. D. Fazakas, G. Eigner, L. Kovács, and L. Szilágyi, “Review of reinforcement learning-based control algorithms in artificial pancreas systems for diabetes mellitus management,” in 2024 IEEE 18th International Symposium on Applied Computational Intelligence and Informatics (SACI). IEEE, 2024, pp. 000 565–000 572.
  15. M. A. Makroum, M. Adda, A. Bouzouane, and H. Ibrahim, “Machine learning and smart devices for diabetes management: Systematic review,” Sensors, vol. 22, no. 5, p. 1843, 2022.
  16. A. Z. Woldaregay, E. Årsand, T. Botsis, D. Albers, L. Mamykina, and G. Hartvigsen, “Data-driven blood glucose pattern classification and anomalies detection: machine-learning applications in type 1 diabetes,” Journal of medical Internet research, vol. 21, no. 5, p. e11030, 2019.
  17. T. Zhu, K. Li, P. Herrero, and P. Georgiou, “Personalized blood glucose prediction for type 1 diabetes using evidential deep learning and meta-learning,” IEEE Transactions on Biomedical Engineering, vol. 70, no. 1, pp. 193–204, 2022.
  18. Y. Han, D.-Y. Kim, J. Woo, and J. Kim, “Glu-ensemble: An ensemble deep learning framework for blood glucose forecasting in type 2 diabetes patients,” Heliyon, vol. 10, no. 8, 2024.
  19. F. Prendin, J. Pavan, G. Cappon, S. Del Favero, G. Sparacino, and A. Facchinetti, “The importance of interpreting machine learning models for blood glucose prediction in diabetes: an analysis using shap,” Scientific reports, vol. 13, no. 1, p. 16865, 2023.
  20. P. Viroonluecha, E. Egea-Lopez, and J. Santa, “Evaluation of offline reinforcement learning for blood glucose level control in type 1 diabetes,” IEEE Access, vol. 11, pp. 104 643–104 655, 2023.
  21. E. Afsaneh, A. Sharifdini, H. Ghazzaghi, and M. Z. Ghobadi, “Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review,” Diabetology & Metabolic Syndrome, vol. 14, no. 1, p. 196, 2022.
  22. W. Gu and S. Wang, “An improved strategy for blood glucose control using multi-step deep reinforcement learning,” arXiv preprint https://arxiv.org/abs/2403.07566, 2024.
  23. L. Pan, W. Sun, W. Wan, Q. Zeng, and J. Xu, “Research progress of diabetic disease prediction model in deep learning,” Journal of Theory and Practice of Engineering Science, vol. 3, no. 12, pp. 15–21, 2023.
  24. K.-L. A. Yau, Y.-W. Chong, X. Fan, C. Wu, Y. Saleem, and P.-C. Lim, “Reinforcement learning models and algorithms for diabetes management,” IEEE Access, vol. 11, pp. 28 391–28 415, 2023.
  25. P. Domanski, A. Ray, F. Firouzi, K. Lafata, K. Chakrabarty, and D. Pflüger, “Blood glucose prediction for type-1 diabetics using deep reinforcement learning,” in 2023 IEEE International Conference on Digital Health (ICDH). IEEE, 2023, pp. 339–347.
  26. I. Fox, “Machine learning for physiological time series: Representing and controlling blood glucose for diabetes management,” Ph.D. dissertation, 2020.
  27. H. Y. Lu, X. Ding, J. E. Hirst, Y. Yang, J. Yang, L. Mackillop, and D. A. Clifton, “Digital health and machine learning technologies for blood glucose monitoring and management of gestational diabetes,” IEEE reviews in biomedical engineering, vol. 17, pp. 98–117, 2023.
  28. S. G. James, M. E. G. Armstrong, A. A. O’Kane, H. Emerson, and Z. S. Abdallah, “Brist1d blood glucose prediction competition,” https://kaggle.com/competitions/brist1d, 2024, kaggle.
  29. J. Xiao, B. Chen, L. Chen, Q. Wang, S. Tan, H. Yuan, D. Xiang, B. Zhang, X. Li, S. Huang et al., “Interpretable time-series neural turing machine for prognostic prediction of patients with type 2 diabetes in physician-pharmacist collaborative clinics,” International Journal of Medical Informatics, vol. 195, p. 105737, 2025.
  30. S. Rancati, P. Bosoni, R. Schiaffini, A. Deodati, P. A. Mongini, L. Sacchi, C. Toffanin, and R. Bellazzi, “Exploration of foundational models for blood glucose forecasting in type-1 diabetes pediatric patients,” Diabetology, vol. 5, no. 6, pp. 584–599, 2024.
  31. A. Wu, E. Singh, I. Zhang, A. Bilal, A. Casu, and R. Pratley, “Machine learning prediction of severity and duration of hypoglycemic events in type 1 diabetes patients,” in The International FLAIRS Conference Proceedings, vol. 37, 2024.