Reproduce “A Real-Time Digital Twin for Type 1 Diabetes using Simulation-Based Inference” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Trung-Dung Hoang, Alceu Bissoto, Vihangkumar V. Naik, Tim Flühmann, Artemii Shlychkov, Jose Garcia-Tirado, Lisa M. Koch
The authors present a simulation-based inference method for estimating person-specific diabetes physiology and starting states from glucose-monitor traces. It learns from simulated data and estimates posterior distributions over model settings. In simulated tests, ReplayBG fit observed days better, while the method had lower reconstruction error on next-day and altered-meal cases, but has not been validated on real patients.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.