High-performance Uncertainty Quantification in Large-scale Virtual Clinical Trials of Closed-loop Diabetes Treatment

TL;DR

This paper introduces a high-performance virtual clinical trial platform for large-scale, risk-free testing of closed-loop diabetes treatments, enabling rapid assessment of treatment performance and uncertainty quantification.

Contribution

The paper presents a novel high-performance software and hardware framework for conducting large-scale virtual clinical trials in diabetes treatment, significantly reducing simulation time.

Findings

Successful simulation of one million patients in 1 hour and 22 minutes.

Effective quantification of uncertainty in treatment performance.

Versatile testing of various control strategies.

Abstract

In this paper, we propose a virtual clinical trial for assessing the performance and identifying risks in closed-loop diabetes treatments. Virtual clinical trials enable fast and risk-free tests of many treatment variations for large populations of fictive patients (represented by mathematical models). We use closed-loop Monte Carlo simulation, implemented in high-performance software and hardware, to quantify the uncertainty in treatment performance as well as to compare the performance in different scenarios or of different closed-loop treatments. Our software can be used for testing a wide variety of control strategies ranging from heuristical approaches to nonlinear model predictive control. We present an example of a virtual clinical trial with one million patients over 52 weeks, and we use high-performance software and hardware to conduct the virtual trial in 1 h and 22 min.