A next-generation platform for diabetes management
-
Updated
Jun 4, 2026 - C#
A next-generation platform for diabetes management
ReplayBG is a digital twin-based methodology to assess new strategies for type 1 diabetes management.
Project to improve BG prediction quality in medical applications using Deep Reinforcement Learning
macOS toolbar glucose viewer
A personal BG display + alert system using the Nightscout API (Dexcom G7 via Nightscout).
Data processing and analysis for "Determining the optimal timing for insulin injection to minimize glucose level variability after a meal in ideal conditions" - a research project for the IB Standard Level Mathematics Analysis and Approaches course inspired by my type 1 diabetes.
AI application for Type 1 Diabetes monitoring, leveraging Open Food Fact database and Freestyle Libre data
Bolus insulin calculator for T1D
Open-source non-commercial Telegram bot for type 1 diabetes — food photo → AI carb counting → bread units → diary. Self-hosted, bilingual (RU/EN). Python + litellm + Gemini Vision + aiosqlite. Active dev, contributors welcome under PolyForm Noncommercial 1.0.0.
A seed-driven simulator for generating synthetic Type 1 Diabetes blood glucose data.
Reproducible ML pipeline for short-term blood glucose prediction in Type 1 Diabetes.
Android CGM companion app — glucose display, graph, alerts, and Nightscout upload
Nightscout Client, to display Continuous Glucose Monitor and/or Insulin Pump Data on your ROKU Platform as a Roku App and/or Screensaver (requires Nightscout Server Setup from https://nightscout.github.io/)
501(c)(3) nonprofit advancing Type 1 Diabetes equity and education | 12 university chapters | 1200+ volunteers
Public showcase for DoseCalc. Architecture, screenshots, code excerpts.
This repository provides the necessary code to reproduce the meta analysis conducted in the scientific work that arose from the following research question: what is the effect of automated insulin delivery system use on diabetes distress?
Causal mediation analysis of CGM data using autoencoder-learned representations to study how meal carbohydrates affect postprandial glucose through insulin bolus decisions.
桌面血糖鐘 · Cross-platform desktop blood glucose widget for Nightscout — macOS / Windows · 繁中 / 简中 / English / 日本語
We present GUIDE (Glucose Intelligence Decision Engine), an RL-based framework that generates patient-specific recommendations for insulin and carbohydrate intake, adapting to individual glucose dynamics and daily routines
Add a description, image, and links to the type-1-diabetes topic page so that developers can more easily learn about it.
To associate your repository with the type-1-diabetes topic, visit your repo's landing page and select "manage topics."