Implementation of a Federated Learning Platform for Glucose Prediction in Type 1 Diabetes

This work tests the implementation of Federated Learning to develop Deep Learning algorithms for glucose prediction in Type 1 Diabetes. A Long-short Term Memorymodel was implemented to predict glucose levels with a forecasting horizon of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{3 0}$</tex> minutes. The model was trained using both centralized learning and Federated Learning in parallel, employing different aggregation strategies such as FedAvg, FedMedian, and FedTrimmedAvg. The resulting models were evaluated using metrics recommended for glucose predictions, and the results obtained from both training paradigms were compared. The predictive capabilities of the federated models and the feasibility of adopting the federated paradigm in this specific application were demonstrated.