ReplayBG¶

A digital-twin based framework for the development and assessment of new algorithms for type 1 diabetes management.

🧬

Digital Twin¶

ReplayBG fits a physiological ODE model to a person's CGM + insulin + meal data (twinning), producing a personalized digital twin of their glucose–insulin system.

🔬

State of the Art¶

Built on validated T1D physiological models and a principled MAP identification procedure, and integrated with AGATA for standardized glucose-metric analysis.

⚡

Easy to Use¶

A tiny API — twin() and replay() — lets you ask what-if: what would this person's glucose have looked like with a different dose, a different meal, or a control algorithm in the loop?

What is ReplayBG?¶

ReplayBG is a digital-twin framework for Type 1 Diabetes (T1D) glucose dynamics. It works in two steps:

Twinning — it fits a physiological model to a person's recorded CGM, insulin and meal data, estimating the parameter set (theta) that best explains that data. This fitted model is the digital twin.
Replay — it forward-simulates the twin under counterfactual scenarios: a different insulin dose, a modified meal, a bolus calculator, a hypo-treatment policy, or a full control algorithm in the loop — and predicts the resulting glucose trace.

 raw DataFrame            Data class              Model (Numba jitclass)
 t, glucose, cho,   ─▶   SingleMealT1DData  ─▶   SingleMealT1DModel   ─┐
 bolus, basal, ...       MultiMealT1DData        MultiMealT1DModel     │
                         MultiMealExtended…      MultiMealExtended…    │
        ┌──────────────────────────────────────────────────────────  ┘
        │
        ├─▶  rbg.twin()    MAP estimation (multi-start Powell + polish)  ─▶  theta (the digital twin)
        │
        └─▶  rbg.replay()  forward simulation with theta                 ─▶  predicted glucose trace

Ready to build your first digital twin? Head to Getting Started.

Reference¶

If you use ReplayBG in your research, please cite:

G. Cappon, M. Vettoretti, G. Sparacino, S. Del Favero, and A. Facchinetti, "ReplayBG: A Digital Twin-Based Methodology to Identify a Personalized Model From Type 1 Diabetes Data and Simulate Glucose Concentrations to Assess Alternative Therapies," IEEE Transactions on Biomedical Engineering, vol. 70, no. 11, pp. 3227–3238, Nov. 2023, doi: 10.1109/TBME.2023.3286856.

@article{cappon2023replaybg,
  author  = {Cappon, Giacomo and Vettoretti, Martina and Sparacino, Giovanni and Del Favero, Simone and Facchinetti, Andrea},
  title   = {{ReplayBG}: A Digital Twin-Based Methodology to Identify a Personalized Model From Type 1 Diabetes Data and Simulate Glucose Concentrations to Assess Alternative Therapies},
  journal = {IEEE Transactions on Biomedical Engineering},
  volume  = {70},
  number  = {11},
  pages   = {3227--3238},
  year    = {2023},
  doi     = {10.1109/TBME.2023.3286856},
}

Supporting research¶

Research on ReplayBG development¶

Journal Papers¶

F. Prendin, A. Facchinetti, and G. Cappon "Data Augmentation via Digital Twins Enables the Development of Personalized Deep Learning Glucose Prediction Algorithms for Type 1 Diabetes in Poor Data Context" IEEE Journal of Biomedical Health Informatics, (under revision, submitted October 2024)
G. Cappon, and A. Facchinetti, "Digital twins in type 1 diabetes: A systematic review" Journal of Diabetes Science and Technology, online ahead of print, 2024, DOI: 10.1177/1932296824126211.
G. Cappon, M. Vettoretti, G. Sparacino, S. Del Favero, and A. Facchinetti "ReplayBG: a digital twin-based methodology to identify a personalized model from type 1 diabetes data and simulate glucose concentrations to assess alternative therapies", IEEE Transactions on Biomedical Engineering, vol. 70, no. 11, pp. 3105-3115, Nov 2023, DOI: 10.1109/TBME.2023.3286856

Conference papers and abstracts¶

G. Cappon, S. Del Favero, and A. Facchinetti "Extending the applicability of ReplayBG tool for digital twinning in type 1 diabetes from single-meal to multi-day scenarios" in the 24th Annual Diabetes Technology Meeting – DTM, Burlingame, CA, USA, October 15-17, 2024.
J. Leth, H. Ghazaleh, H. Peuscher, and G. Cappon "The potential of open-source software in diabetes research" in the 17th International Conference on Advanced Technology & Treatment for Diabetes – ATTD, Firenze, Italy, March 6-9, 2024 (invited oral presentation, speaker J. Leth).
H. Peuscher, G. Cappon, A. Cinar, J. Deichmann, H. Ghazaleh, H. Kaltenbach, L. Sandini, M. Siket, J. Xie, and X. Zhou "A survey on existing open-source projects in diabetes simulation" in the 17th International Conference on Advanced Technology & Treatment for Diabetes – ATTD, Firenze, Italy, March 6-9, 2024 (invited oral presentation, speaker J. Leth).
G. Cappon, M. Vettoretti, G. Sparacino, S. Del Favero, and A. Facchinetti "Expanding ReplayBG simulation methodology domain of validity to single day multiple meal scenarios" in the 15th International Conference on Advanced Technology & Treatment for Diabetes – ATTD, Barcelona, Spain, April 27-30, 2022.
G. Cappon, M. Vettoretti, G. Sparacino, S. Del Favero, and A. Facchinetti "ReplayBG provides reliable indications when used to assess meal bolus alterations in type 1 diabetes" in the 14th International Conference on Advanced Technology & Treatment for Diabetes – ATTD, Paris, France, June 2-6, 2021.
G. Cappon, A. Facchinetti, G. Sparacino, and S. Del Favero "ReplayBG: A novel in-silico framework to retrospectively assess new therapy guidelines for type 1 diabetes management" in the 20th Annual Diabetes Technology Meeting – DTM, Bethesda, Maryland, USA, November 12-14, 2020.
G. Cappon, A. Facchinetti, G. Sparacino, and S. Del Favero "A Bayesian framework to personalize glucose prediction in type 1 diabetes using a physiological model" in the 19th Annual Diabetes Technology Meeting – DTM, Bethesda, Maryland, USA, November 14-16, 2019.
G. Cappon, A. Facchinetti, G. Sparacino, and S. Del Favero "A Bayesian framework to identify type 1 diabetes physiological models using easily accessible patient data" in the 41th Annual International Conference of the IEEE Engineering in Medicine and Biology Society – EMBC, Berlin, Germany, July 23-27, 2019 (accepted for oral presentation, speaker G.Cappon).

Research using ReplayBG as component or validation tool¶

Journal Papers¶

E. Pellizzari, G. Cappon, G. Nicolis, G. Sparacino, and A. Facchinetti "Developing effective machine learning models for insulin bolus calculation in type 1 diabetes exploiting real-world data and digital twins" IEEE Transactions on Biomedical Engineering, online ahead of print, Nov 2025, DOI: 10.1109/TBME.2025.3648515
E. Pellizzari, F. Prendin, G. Cappon, G. Sparacino, and A. Facchinetti, "drCORRECT: An algorithm for the preventive administration of postprandial corrective insulin boluses in type 1 diabetes management" Journal of Diabetes Science and Technology, online ahead of print, 2023, DOI: 10.1177/19322968231221768
F. Prendin, J. Pavan, G. Cappon, S. Del Favero, G. Sparacino, and A. Facchinetti, "The importance of interpreting machine learning models for blood glucose prediction in diabetes: an analysis using SHAP" Scientific Reports, vol. 13, no. 1, pp. 16865, Oct 2023, DOI: 10.1038/s41598-023-44155-x.
G. Noaro, G. Cappon, M. Vettoretti, G. Sparacino, S. Del Favero, and A. Facchinetti "Machine-learning based model to improve insulin bolus calculation in type 1 diabetes therapy" IEEE Transactions on Biomedical Engineering, vol. 68, no. 1, pp. 247-255, Jan 2021. DOI: 10.1109/TBME.2020.3004031

Conference papers and abstracts¶

E. Pellizzari, M. Zanon, L. Cossu, P. Herrero, A. Facchinetti, and G. Cappon "Comparing Bayesian Methods for Robust Parameter Estimation in Type 1 Diabetes Digital Twins" in the 19th International Conference on Advanced Technology & Treatment for Diabetes – ATTD, Barcelona, Spain, March 11-14, 2026 (accepted for oral presentation).
L. Cossu, A. Ghiotto, E. Pellizzari, M. Martino, A. Deodati, R. Schiaffini, S. Cianfarani, A. Facchinetti, G. Sparacino, and G. Cappon "Development of a Web Interface for Type 1 Diabetes Therapy Simulation Based on Digital Twin" in the 19th International Conference on Advanced Technology & Treatment for Diabetes – ATTD, Barcelona, Spain, March 11-14, 2026 (accepted for oral presentation).
E. Pellizzari, O. Mujahid, F. Prendin, O. Bustos, G. Cappon, A. Facchinetti, and J. Vehi "Enhancing the physiological plausibility of GAN-generated blood glucose in type 1 diabetes with monotonicity constraints" in the 2025 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering – MetroXRAINE, Ancona, Italy, October 22-24, 2025.
E. Pellizzari, G. Cappon, G. Sparacino, A. Deodati, R. Schiaffini, S. Cianfarani, and A. Facchinetti "Digital-twin based optimization of bolus insulin dosing in pediatric type 1 diabetes: an in silico feasibility study" in the 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society – EMBC, Copenhagen, Denmark, July 14-17, 2025.
L. Cossu, L. Semenzato, A. Facchinetti, and G. Cappon "Digital twin-based reinforcement learning for personalized mealtime insulin dosing in pediatric diabetes: A proof of concept" in the 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society – EMBC, Copenhagen, Denmark, July 14-17, 2025.
L. Cossu, E. Pellizzari, G. Cappon, A. Deodati, R. Schiaffini, G. Sparacino, S. Cianfarani, and A. Facchinetti "Enhancing pediatric type 1 diabetes therapy using TWIN, a clinical decision support system based on digital twins" in the 9th Congress of the National Group of Bioengineering – GNB, Palermo, Italy, Jun 16-18, 2025.
E. Pellizzari, G. Cappon, G. Sparacino, and A. Facchinetti "Digital twin-based adaptive optimization of basal insulin in pediatric patients: A feasibility study" in the 18th International Conference on Advanced Technology & Treatment for Diabetes – ATTD, Amsterdam, The Netherlands, March 19-22, 2025.
E. Pellizzari, G. Cappon, G. Nicolis, G. Sparacino, and A. Facchinetti "Exploiting real-world data and digital twins to develop effective formulas for dosing insulin boluses in type 1 diabetes therapy" in the 24th Annual Diabetes Technology Meeting – DTM, Burlingame, CA, USA, October 15-17, 2024.
F. Prendin, A. Facchinetti, and G. Cappon "Digital twin for data augmentation enables the development of accurate personalized deep glucose forecasting algorithms" in the 24th Annual Diabetes Technology Meeting – DTM, Burlingame, CA, USA, October 15-17, 2024.
E. Pellizzari, F. Prendin, G. Cappon, G. Sparacino, and A. Facchinetti "DR-CIB: An algorithm for the preventive administration of corrective insulin boluses in T1D based on dynamic risk concept and patient-specific timing" in the 23rd Annual Diabetes Technology Meeting – DTM, Online, November 1-4, 2023 (Gold Student Award, accepted for oral presentation, speaker E. Pellizzari).
G. Cappon, E. Pellizzari, L. Cossu, G. Sparacino, A. Deodati, R. Schiaffini, S. Cianfarani, and A. Facchinetti "System architecture of TWIN: A new digital twin-based clinical decision support system for type 1 diabetes management in children" in the 19th International Conference on Body Sensor Networks – BSN, Boston, MA, USA, October 9-11, 2023.
E. Pellizzari, F. Prendin, G. Cappon, G. Sparacino, and A. Facchinetti "A deep-learning based algorithm for the management of hyperglycemia in type 1 diabetes therapy" in the 19th International Conference on Body Sensor Networks – BSN, Boston, MA, USA, October 9-11, 2023.
G. Noaro, G. Cappon, G. Sparacino, and A. Facchinetti "An ensemble learning algorithm based on dynamic voting for targeting the optimal insulin dosage in type 1 diabetes management" in the 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society – EMBC, Guadalajara, Mexico, October 31-4, 2021 (accepted for oral presentation, speaker G. Noaro).
G. Cappon, E. Pighin, F. Prendin, G. Sparacino, and A. Facchinetti "A correction insulin bolus delivery strategy for decision support systems in type 1 diabetes" in the 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society – EMBC, Guadalajara, Mexico, October 31-4, 2021 (accepted for oral presentation, speaker G. Cappon).
G. Noaro, G. Cappon, M. Vettoretti, S. Del Favero, G. Sparacino, and A. Facchinetti "A new model for mealtime insulin dosing in type 1 diabetes: Retrospective validation on CTR3 dataset" in the 20th Annual Diabetes Technology Meeting – DTM, Bethesda, Maryland, USA, November 12-14, 2020 (accepted for oral presentation, speaker G. Noaro).
G. Noaro, G. Cappon, G. Sparacino, S. Del Favero, A. Facchinetti "Nonlinear machine learning models for insulin bolus estimation in type 1 diabetes therapy" in the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society – EMBC, Montreal, Canada, July 20-24, 2020 (accepted for oral presentation, speaker G. Noaro).