Generation of Virtual Patient Populations That Represent Real Type 1 Diabetes Cohorts

Abstract

Preclinical testing and validation of therapeutic strategies developed for patients with type 1 diabetes (T1D) require a cohort of virtual patients (VPs). However, current simulators provide a limited number of VPs, lack real-life scenarios, and inadequately represent intra- and inter-day variability in insulin sensitivity and blood glucose (BG) profile. The generation of a realistic scenario was achieved by using the meal patterns, insulin profiles (basal and bolus), and exercise sessions estimated as disturbances using clinical data from a cohort of 14 T1D patients using the Medtronic 640G insulin pump provided by the Hospital Clínic de Barcelona. The UVa/Padova’s cohort of adult patients was used for the generation of a new cohort of VPs. Insulin model parameters were optimized and adjusted in a day-by-day fashion to replicate the clinical data to create a cohort of 75 VPs. All primary and secondary outcomes reflecting the BG profile of a T1D patient were analyzed and compared to the clinical data. The mean BG 166.3 versus 162.2 mg/dL ( = 0.19), coefficient of variation 32% versus 33% ( = 0.54), and percent of time in range (70 to 180 mg/dL) 59.6% versus 66.8% ( = 0.35) were achieved. The proposed methodology for generating a cohort of VPs is capable of mimicking the BG metrics of a real cohort of T1D patients from the Hospital Clínic de Barcelona. It can adopt the inter-day variations in the BG profile, similar to the observed clinical data, and thus provide a benchmark for preclinical testing of control techniques and therapy strategies for T1D patients.

Dynamic of Glucose Homeostasis in Virtual Patients: A Comparison between Different Behaviors

“…Contrasting the proposed work in relation to the most current works in the literature, it was observed that the main particularity of this work is focused on the study of the effects of factors such as diet and physical activity in healthy people, being the areas of greatest interest those focused on diabetes. Examples of some of the work consulted are Ahmad et al [ 40 ], developing virtual patient populations capable of simulating blood glucose metrics in patients with T1DM; Krishnamoorthy et al [ 41 ] applying in-silico experimentation on 50 virtual patients with T2DM to find optimal insulin dose values; Smaoui et al [ 42 ] developing a platform for the development and in-silico experimentation of experimental protocols in patient with T1DM.…”

An automatic deep reinforcement learning bolus calculator for automated insulin delivery systems

“…A cohort of 68 virtual patients previously developed by our group is considered in this study 39 . A protocol of three meals (breakfast at 08:00 of 30-50g, lunch at 14:00 of 50–70g, and dinner at 20:00 of 60–80g) was considered during the training session.…”

Internal model control based module for the elimination of meal and exercise announcements in hybrid artificial pancreas systems

“…Although the validation included a dierent instance of variability, assessing the module with the same virtual cohort used for tuning it may limit the generalization of the method to real patients. In the future, the subject cohort must be expanded to improve the tuning, for example, using recent subject cloning techniques from clinical data [65]. Even though a more extended population was used to t the regression equations, these equations would only provide an initial tuning; only adapting the parameters would guarantee an acceptable long-term performance against the intra-patient variability.…”