Uncertainty quantification in neural network-based glucose prediction for diabetes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Hai Siong, McBeth, Rafe
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