Uncertainty quantification in neural network-based glucose prediction for diabetes
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910081231093760 |
|---|---|
| author | Tan, Hai Siong McBeth, Rafe |
| author_facet | Tan, Hai Siong McBeth, Rafe |
| contents | In this work, we investigate uncertainty-aware neural network models for blood glucose prediction and adverse glycemic event identification in Type 1 diabetes. We consider three families of sequence models based on LSTM, GRU, and Transformer architectures, with uncertainty quantification enabled by either Monte Carlo dropout or through evidential output layers compatible with Deep Evidential Regression. Using the HUPA-UCM diabetes dataset for validation, we find that Transformer-based models equipped with evidential output heads provide the most effective uncertainty-aware framework, achieving consistently higher predictive accuracies and better-calibrated uncertainty estimates whose magnitudes significantly correlate with prediction errors. We further evaluate the clinical risk of each model using the recently proposed Diabetes Technology Society error grid, with risk categories defined by international expert consensus. Our results demonstrate the value of integrating principled uncertainty quantification into real-time machine-learning-based blood glucose prediction systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04955 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Uncertainty quantification in neural network-based glucose prediction for diabetes Tan, Hai Siong McBeth, Rafe Machine Learning Medical Physics In this work, we investigate uncertainty-aware neural network models for blood glucose prediction and adverse glycemic event identification in Type 1 diabetes. We consider three families of sequence models based on LSTM, GRU, and Transformer architectures, with uncertainty quantification enabled by either Monte Carlo dropout or through evidential output layers compatible with Deep Evidential Regression. Using the HUPA-UCM diabetes dataset for validation, we find that Transformer-based models equipped with evidential output heads provide the most effective uncertainty-aware framework, achieving consistently higher predictive accuracies and better-calibrated uncertainty estimates whose magnitudes significantly correlate with prediction errors. We further evaluate the clinical risk of each model using the recently proposed Diabetes Technology Society error grid, with risk categories defined by international expert consensus. Our results demonstrate the value of integrating principled uncertainty quantification into real-time machine-learning-based blood glucose prediction systems. |
| title | Uncertainty quantification in neural network-based glucose prediction for diabetes |
| topic | Machine Learning Medical Physics |
| url | https://arxiv.org/abs/2603.04955 |