In-silico Risk Analysis of Personalized Artificial Pancreas Controllers via Rare-event Simulation

TL;DR

This paper develops a simulation-based framework using rare-event techniques to assess the safety of personalized artificial pancreas controllers for Type 1 diabetes, enabling efficient risk estimation of adverse events.

Contribution

It introduces a novel in-silico risk analysis method combining patient-specific models with rare-event simulation to evaluate artificial pancreas safety.

Findings

72,000× faster simulation speed than real-time

2-10× increase in sampling adverse conditions

Order of magnitude reduction in required simulations

Abstract

Modern treatments for Type 1 diabetes (T1D) use devices known as artificial pancreata (APs), which combine an insulin pump with a continuous glucose monitor (CGM) operating in a closed-loop manner to control blood glucose levels. In practice, poor performance of APs (frequent hyper- or hypoglycemic events) is common enough at a population level that many T1D patients modify the algorithms on existing AP systems with unregulated open-source software. Anecdotally, the patients in this group have shown superior outcomes compared with standard of care, yet we do not understand how safe any AP system is since adverse outcomes are rare. In this paper, we construct generative models of individual patients' physiological characteristics and eating behaviors. We then couple these models with a T1D simulator approved for pre-clinical trials by the FDA. Given the ability to simulate patient outcomes in-silico, we utilize techniques from rare-event simulation theory in order to efficiently quantify the performance of a device with respect to a particular patient. We show a 72,000$\times$ speedup in simulation speed over real-time and up to 2-10 times increase in the frequency which we are able to sample adverse conditions relative to standard Monte Carlo sampling. In practice our toolchain enables estimates of the likelihood of hypoglycemic events with approximately an order of magnitude fewer simulations.