Creative Commons source reading · Machine learning for performance
Hybrid Digital Twin Framework for Personalized Diabetes Management Using Mathematical Modelling and Machine Learning
Vathana Dennish; Babu Subramani; Vijayakumar Ponnusamy; Suganthi Kuppusamy; Janardhanan Subramonia Kumar; Nemanja Zdravković; Miloš Kostić
Originally published in Diagnostics (Basel) · 2026-09-01
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
Background/Objectives: Diabetes mellitus is a chronic metabolic disorder characterized by impaired regulation of blood glucose due to defects in insulin secretion, insulin action, or both. Physiological and lifestyle factors vary among individuals. General medicine is not applicable to all patients. In this scenario, personalized medicine for each individual becomes costly. Effective management of continuous glucose levels with accurate insulin dosage is challenging. To overcome this, a digital twin (DT)-based insulin dosage simulator with an individual’s metabolic system is proposed in this work. Methods: Various machine learning techniques, mathematical models of physiology, and risk assessment using probability are used to predict the dynamics of patient-specific glucose–insulin. Parameters such as carbohydrate intake, sleep…
7. Results and Discussion
The proposed model of DT simulation results demonstrates that the model can reproduce realistic fluctuations in glucose, which are driven by meals, influenced by the circadian cycle, and influenced by physical activity. The following outcomes are obtained from the DT model: 1. Glucose prediction (post-meal):Both the magnitude and timing of glucose peaks are captured after carbohydrate intake. The system provides accurate predictions of postprandial glucose excursions. 2. Outcome of physical activity: During and after exercise sessions, glucose levels decrease, and this is effectively modelled with simulations. Physical activity impacts glucose reduction. 3. Significance of circadian modelling: When modelling glucose dynamics at different times of the day, incorporating circadian variations in insulin sensitivity will improve overall…
8. Conclusions
The proposed DT system framework combines physiological modelling, lifestyle factor analysis, predictive components, probabilistic risk assessment, and interpretability features within a single integrated framework. Simulation results showed that the approach provides more accurate glucose predictions, improved identification of glycemic risk conditions, and more tailored insulin dosing than conventional methods. These findings suggest that the DT approach can serve as an effective tool for clinical decision support and personalized treatment planning in diabetes management. Future work will involve connecting the framework with real-time continuous glucose monitoring systems, validating its performance using clinical datasets, and further enhancing its personalization and interpretability for practical use in the healthcare sector.…
Editorial reading guide
- What data created and tested the model, and was evaluation independent?
- What is the cost of a false positive, false negative or out-of-distribution decision?
