Interpreting deep glucose predictive models for diabetic people using RETAIN - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Interpreting deep glucose predictive models for diabetic people using RETAIN

Mounim El Yacoubi
Mehdi Ammi

Résumé

Progress in the biomedical field through the use of deep learning is hindered by the lack of interpretability of the models. In this paper, we study the RETAIN architecture for the forecasting of future glucose values for diabetic people. Thanks to its two-level attention mechanism, the RETAIN model is interpretable while remaining as efficient as standard neural networks.We evaluate the model on a real-world type-2 diabetic population and we compare it to a random forest model and a LSTM-based recurrent neural network. Our results show that the RETAIN model outperforms the former and equals the latter on common accuracy metrics and clinical acceptability metrics, thereby proving its legitimacy in the context of glucose level forecasting. Furthermore, we propose tools to take advantage of the RETAIN interpretable nature. As informative for the patients as for the practitioners, it can enhance the understanding of the predictions made by the model and improve the design of future glucose predictive models.

Dates et versions

hal-04307918 , version 1 (26-11-2023)

Identifiants

Citer

Maxime de Bois, Mounim El Yacoubi, Mehdi Ammi. Interpreting deep glucose predictive models for diabetic people using RETAIN. International Conference on Pattern Recognition and Artificial Intelligence ( IPCRAI), Oct 2010, Virtual conference, China. pp.685-694, ⟨10.1007/978-3-030-59830-3_59⟩. ⟨hal-04307918⟩
15 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More