A Comparative Study of Transformer-Based Models for Multi-Horizon Blood Glucose Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Karagoz, Meryem Altin, Breton, Marc D., Fathi, Anas El
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909609471508480
author Karagoz, Meryem Altin
Breton, Marc D.
Fathi, Anas El
author_facet Karagoz, Meryem Altin
Breton, Marc D.
Fathi, Anas El
contents Accurate blood glucose prediction can enable novel interventions for type 1 diabetes treatment, including personalized insulin and dietary adjustments. Although recent advances in transformer-based architectures have demonstrated the power of attention mechanisms in complex multivariate time series prediction, their potential for blood glucose (BG) prediction remains underexplored. We present a comparative analysis of transformer models for multi-horizon BG prediction, examining forecasts up to 4 hours and input history up to 1 week. The publicly available DCLP3 dataset (n=112) was split (80%-10%-10%) for training, validation, and testing, and the OhioT1DM dataset (n=12) served as an external test set. We trained networks with point-wise, patch-wise, series-wise, and hybrid embeddings, using CGM, insulin, and meal data. For short-term blood glucose prediction, Crossformer, a patch-wise transformer architecture, achieved a superior 30-minute prediction of RMSE (15.6 mg / dL on OhioT1DM). For longer-term predictions (1h, 2h, and 4h), PatchTST, another path-wise transformer, prevailed with the lowest RMSE (24.6 mg/dL, 36.1 mg/dL, and 46.5 mg/dL on OhioT1DM). In general, models that used tokenization through patches demonstrated improved accuracy with larger input sizes, with the best results obtained with a one-week history. These findings highlight the promise of transformer-based architectures for BG prediction by capturing and leveraging seasonal patterns in multivariate time-series data to improve accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08821
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Comparative Study of Transformer-Based Models for Multi-Horizon Blood Glucose Prediction
Karagoz, Meryem Altin
Breton, Marc D.
Fathi, Anas El
Quantitative Methods
Artificial Intelligence
Applications
Accurate blood glucose prediction can enable novel interventions for type 1 diabetes treatment, including personalized insulin and dietary adjustments. Although recent advances in transformer-based architectures have demonstrated the power of attention mechanisms in complex multivariate time series prediction, their potential for blood glucose (BG) prediction remains underexplored. We present a comparative analysis of transformer models for multi-horizon BG prediction, examining forecasts up to 4 hours and input history up to 1 week. The publicly available DCLP3 dataset (n=112) was split (80%-10%-10%) for training, validation, and testing, and the OhioT1DM dataset (n=12) served as an external test set. We trained networks with point-wise, patch-wise, series-wise, and hybrid embeddings, using CGM, insulin, and meal data. For short-term blood glucose prediction, Crossformer, a patch-wise transformer architecture, achieved a superior 30-minute prediction of RMSE (15.6 mg / dL on OhioT1DM). For longer-term predictions (1h, 2h, and 4h), PatchTST, another path-wise transformer, prevailed with the lowest RMSE (24.6 mg/dL, 36.1 mg/dL, and 46.5 mg/dL on OhioT1DM). In general, models that used tokenization through patches demonstrated improved accuracy with larger input sizes, with the best results obtained with a one-week history. These findings highlight the promise of transformer-based architectures for BG prediction by capturing and leveraging seasonal patterns in multivariate time-series data to improve accuracy.
title A Comparative Study of Transformer-Based Models for Multi-Horizon Blood Glucose Prediction
topic Quantitative Methods
Artificial Intelligence
Applications
url https://arxiv.org/abs/2505.08821