A Real-Time Digital Twin for Type 1 Diabetes using Simulation-Based Inference

2025-07-02

AI Summary

To address the high computational cost and poor generalizability in estimating high-dimensional physiological parameters for Type 1 Diabetes (T1D) digital twins, this paper proposes a Simulation-Based Inference (SBI)-driven neural posterior estimation framework. The method couples mechanistic physiological models with deep generative models and employs end-to-end amortized training to enable fast, differentiable posterior inference. Compared to conventional MCMC approaches, our framework significantly improves estimation accuracy and cross-scenario generalizability, achieves millisecond-scale single-inference latency, and supports real-time glucose–insulin dynamic modeling. It further delivers well-calibrated uncertainty quantification. Extensive experiments on synthetic data and preclinical simulations demonstrate superior performance across key metrics. This work establishes an efficient, robust foundation for reliable parameter inference in T1D digital twin systems.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Probabilistic Inference

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurately estimating parameters of physiological models is essential to achieving reliable digital twins. For Type 1 Diabetes, this is particularly challenging due to the complexity of glucose-insulin interactions. Traditional methods based on Markov Chain Monte Carlo struggle with high-dimensional parameter spaces and fit parameters from scratch at inference time, making them slow and computationally expensive. In this study, we propose a Simulation-Based Inference approach based on Neural Posterior Estimation to efficiently capture the complex relationships between meal intake, insulin, and glucose level, providing faster, amortized inference. Our experiments demonstrate that SBI not only outperforms traditional methods in parameter estimation but also generalizes better to unseen conditions, offering real-time posterior inference with reliable uncertainty quantification.

Problem

• Estimating physiological model parameters for diabetes digital twins
• Overcoming complexity in glucose-insulin interaction modeling
• Replacing slow traditional methods with fast Simulation-Based Inference

Innovation

• Simulation-Based Inference for parameter estimation
• Neural Posterior Estimation for complex relationships
• Real-time posterior inference with uncertainty quantification