Incorporating Uncertainty Estimation and Interpretability to Personalised Glucose Prediction Using the Temporal Fusion Transformer.

More than 14% of the world’s population suffered from diabetes mellitus in 2022. This metabolic condition is defined by increased blood glucose concentration. Among the different types of diabetes, type 1 diabetes, caused by a lack of insulin secretion, has a particularly challenging treatment. In this regard, automatic glucose level estimation implements Continuous Glucose Monitoring (CGM) devices, showing positive therapeutic outcomes. AI-based glucose prediction has commonly followed a deterministic approach, usually with lack of interpretability. Therefore, these AI-based methods do not provide enough information in critical decision-making scenarios, like in the medical field. This work intends to provide accurate, interpretable, and personalized glucose prediction using the Temporal Fusion Transformer (TFT), also including uncertainty estimation. The TFT was trained using two databases, an in-house collected dataset and the OhioT1DM dataset, commonly used for glucose forecasting benchmarking. For both datasets, the set of input features to train the model was varied to assess its impact on model interpretability and prediction performance. Models were evaluated using common prediction metrics, diabetes-specific metrics, uncertainty estimation and interpretability of the model, including feature importance and attention. Obtained results showed that TFT outperforms in terms of RMSE by at least 13% existing methods for both datasets.