Daily Rhythms in Blood Glucose: Time-of-Day Forecasts in Type 2 Diabetes

Working Paper
Data Science
Authors

N.P.B. Pedersen

T.K. Bugajski

J.E. Vera-Valdés

S.H. Casper

M.H. Jensen

P. Vestergaard

T. Kronborg

Published

2025

Abstract

Background: Accurate and interpretable forecasting of blood glucose levels is critical for effective management of Type 2 diabetes. While complex machine learning models offer high predictive accuracy, their opacity often limits clinical applicability. This study investigates the performance of a simple, interpretable reference model: the time-of-day mean forecast.

Method: The proposed approach divides each 24-hour period into discrete time sequences and, for each sequence, computes the mean glucose value across previous days. This methodology captures intra-day regularities in glucose dynamics and implicitly accounts for circadian influences, such as variations in insulin sensitivity and hepatic glucose production.

Results: The model reflects intra-day glucose patterns and identifies clinically relevant periods of elevated variability, such as the postprandial and nocturnal windows. Forecasting performance improves with increased temporal granularity: in 91.84% of the individuals, at least one finer bin size outperformed the naïve baseline. Where, 51% achieved optimal performance using the highest resolution with a 5-minute bin size. Compared to the naïve approach, the 5-minute bin size reduced mean squared error by an average of 12.2%.

Conclusions: We have justified the time-of-day approach using a simple mean forecast model, showing that aligning prediction windows with time-of-day patterns enhances forecast accuracy. Building on this foundation, the time-of-day mean forecast serves as a practical benchmark. Future work should explore more complex models that incorporate individual covariates and dynamic temporal dependencies, while maintaining interpretability using the described temporal structure.

Download

The paper can be freely downloaded in medRxiv here.