https://github.com/keawang/differentiable_t1d
Differentiable simulators for Type 1 Diabetes research in Jax and PyTorch
https://github.com/keawang/differentiable_t1d
cgm diabetes differential-equations dynamical-systems glucose insulin jax python pytorch simulator t1d
Last synced: 22 days ago
JSON representation
Differentiable simulators for Type 1 Diabetes research in Jax and PyTorch
- Host: GitHub
- URL: https://github.com/keawang/differentiable_t1d
- Owner: KeAWang
- Created: 2022-10-26T03:08:22.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2023-08-25T01:44:34.000Z (over 1 year ago)
- Last Synced: 2025-03-25T06:24:36.487Z (about 1 month ago)
- Topics: cgm, diabetes, differential-equations, dynamical-systems, glucose, insulin, jax, python, pytorch, simulator, t1d
- Language: Python
- Homepage:
- Size: 6.3 MB
- Stars: 7
- Watchers: 1
- Forks: 0
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Differentiable T1D Simulators
This repository contains various simulators/dynamical systems for modeling Type 1 Diabetes (T1D) dynamics.
We implement our models in Jax and PyTorch, allowing for easy differentiation of the dynamics.
**Examples**
See the `examples` folder for examples of how to generate data using our simulators.
**Installation**
1. Clone the repository: `git clone [email protected]:KeAWang/differentiable_t1d.git`
2. `pip install ./differentiable_t1d`
**Supported dynamics**
- UVa/Padova 2008 simulator. See *Kovatchev et al., 2009. In silico preclinical trials: a proof of concept in closed-loop control of type 1 diabetes.*
- Medtronic Virtual Patient (MVP) model. See *Kanderian et al., 2009. Identification of Intraday Metabolic Profiles during Closed-Loop Glucose Control in Individuals with Type 1 Diabetes*