Previous Article in Journal
Feature Selection Method Based on Simultaneous Perturbation Stochastic Approximation Technique Evaluated on Cancer Genome Data Classification
Previous Article in Special Issue
A Hybrid Steffensen–Genetic Algorithm for Finding Multi-Roots of Nonlinear Equations and Applications to Biomedical Engineering
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Hybrid Stochastic–Machine Learning Framework for Postprandial Glucose Prediction in Type 1 Diabetes

1
Department of Mathematics, University of Architecture, Civil Engineering and Geodesy, 1 Hristo Smirnenski Blvd., 1164 Sofia, Bulgaria
2
Faculty of Fire Safety and Civil Protection, Academy of the Ministry of Interior, 170 Pirotska Str., 1309 Sofia, Bulgaria
3
Department of Statistics and Econometrics, Faculty of Economics and Business Administration, Sofia University ‘St. Kliment Ohridski’, 125 Tsarigradsko Shosse Blvd., bl. 3, 1113 Sofia, Bulgaria
*
Author to whom correspondence should be addressed.
Algorithms 2025, 18(10), 623; https://doi.org/10.3390/a18100623
Submission received: 1 August 2025 / Revised: 13 September 2025 / Accepted: 24 September 2025 / Published: 1 October 2025

Abstract

This research introduces a hybrid framework that integrates stochastic modeling and machine learning for predicting postprandial glucose levels in individuals with Type 1 Diabetes (T1D). The primary aim is to enhance the accuracy of glucose predictions by merging a biophysical Glucose–Insulin–Meal (GIM) model with advanced machine learning techniques. This framework is tailored to utilize the Kaggle BRIST1D dataset, which comprises real-world data from continuous glucose monitoring (CGM), insulin administration, and meal intake records. The methodology employs the GIM model as a physiological prior to generate simulated glucose and insulin trajectories, which are then utilized as input features for the machine learning (ML) component. For this component, the study leverages the Light Gradient Boosting Machine (LightGBM) due to its efficiency and strong performance with tabular data, while Long Short-Term Memory (LSTM) networks are applied to capture temporal dependencies. Additionally, Bayesian regression is integrated to assess prediction uncertainty. A key advancement of this research is the transition from a deterministic GIM formulation to a stochastic differential equation (SDE) framework, which allows the model to represent the probabilistic range of physiological responses and improves uncertainty management when working with real-world data. The findings reveal that this hybrid methodology enhances both the precision and applicability of glucose predictions by integrating the physiological insights of Glucose Interaction Models (GIM) with the flexibility of data-driven machine learning techniques to accommodate real-world variability. This innovative framework facilitates the creation of robust, transparent, and personalized decision-support systems aimed at improving diabetes management.
Keywords: glucose–insulin model; stochastic differential equations; machine learning; type 1 diabetes; PID controller; hybrid modeling; physiological simulation glucose–insulin model; stochastic differential equations; machine learning; type 1 diabetes; PID controller; hybrid modeling; physiological simulation

Share and Cite

MDPI and ACS Style

Naskinova, I.; Kolev, M.; Karova, D.; Milev, M. Hybrid Stochastic–Machine Learning Framework for Postprandial Glucose Prediction in Type 1 Diabetes. Algorithms 2025, 18, 623. https://doi.org/10.3390/a18100623

AMA Style

Naskinova I, Kolev M, Karova D, Milev M. Hybrid Stochastic–Machine Learning Framework for Postprandial Glucose Prediction in Type 1 Diabetes. Algorithms. 2025; 18(10):623. https://doi.org/10.3390/a18100623

Chicago/Turabian Style

Naskinova, Irina, Mikhail Kolev, Dilyana Karova, and Mariyan Milev. 2025. "Hybrid Stochastic–Machine Learning Framework for Postprandial Glucose Prediction in Type 1 Diabetes" Algorithms 18, no. 10: 623. https://doi.org/10.3390/a18100623

APA Style

Naskinova, I., Kolev, M., Karova, D., & Milev, M. (2025). Hybrid Stochastic–Machine Learning Framework for Postprandial Glucose Prediction in Type 1 Diabetes. Algorithms, 18(10), 623. https://doi.org/10.3390/a18100623

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop