University of Leicester
1-s2.0-S0169260722002449-main.pdf (1.4 MB)

Generation of post-meal insulin correction boluses in type 1 diabetes simulation models for in-silico clinical trials: More realistic scenarios obtained using a decision tree approach

Download (1.4 MB)
journal contribution
posted on 2022-08-31, 14:21 authored by N. Camerlingo, M. Vettoretti, S. Del Favero, A. Facchinetti, P. Choudhary, G. Sparacino
Background and objective: In type 1 diabetes (T1D) research, in-silico clinical trials (ISCTs) notably facilitate the design/testing of new therapies. Published simulation tools embed mathematical models of blood glucose (BG) and insulin dynamics, continuous glucose monitoring (CGM) sensors, and insulin treatments, but lack a realistic description of some aspects of patient lifestyle impacting on glucose control. Specifically, to effectively simulate insulin correction boluses, required to treat post-meal hyperglycemia (BG > 180 mg/dL), the timing of the bolus may be influenced by subjects’ behavioral attitudes. In this work, we develop an easily interpretable model of the variability of correction bolus timing observed in real data, and embed it into a popular simulation tool for ISCTs. Methods: Using data collected in 196 adults with T1D monitored in free-living conditions, we trained a decision tree (DT) model to classify whether a correction bolus is injected in a future time window, based on predictors collected back in time, related to CGM data, previous insulin boluses and subject's characteristics. The performance was compared to that of a logistic regression classifier with LASSO regularization (LC), trained on the same dataset. After validation, the DT was embedded within a popular T1D simulation tool and an ISCT was performed to compare the simulated correction boluses against those observed in a subset of data not used for model training. Results: The DT provided better classification performance (accuracy: 0.792, sensitivity: 0.430, specificity: 0.878, precision: 0.455) than the LC and presented good interpretability. The most predictive features were related to CGM (and its temporal variations), time since the last insulin bolus, and time of the day. The correction boluses simulated by the DT, after implementation in the simulation tool, showed a good agreement with real-world data. Conclusions: The DT developed in this work represents a simple set of rules to mimic the same timing of correction boluses observed on real data. The inclusion of the model in simulation tools allows investigators to perform ISCTs that more realistically represent the patient behavior in taking correction boluses and the post-prandial BG response. In the future, more complex models can be investigated.


This study is part of the Hypo-RESOLVE project. The project has received funding from the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No. 777460. The JU re- ceives support from the European Union’s Horizon 2020 research and innovation program and EFPIA and T1D Exchange, JDRF, In- ternational Diabetes Federation (IDF), The Leona M. and Harry B. Helmsley Charitable Trust.



Computer Methods and Programs in Biomedicine 221(2022)106862

Author affiliation

Leicester Diabetes Centre


  • VoR (Version of Record)

Published in

Computer Methods and Programs in Biomedicine









Acceptance date


Copyright date


Available date


Spatial coverage