Insulin Omission Surrogate (iOS)

Overview

Type 1 Diabetes management is requiring and implies numerous lifestyle modifications. Insulin restriction to control weight is a frequent phenomenon, affecting up to 40% of PWT1D. Broadly, purging or binge eating behaviors are also frequently disordered eating behaviors (DEB) in people living with a Type 1 Diabetes (associated or not with restrictive eating behaviors). In a study on adolescents with T1D, the prevalence of moderate or high level of DEB ranged from 21% to 32%. Moreover, the presence of binge eating behavior seems to be associated with higher anxiety and depression levels. Omitting insulin for weight control has been associated with the highest rates of retinopathy and nephropathy when compared to other weight control behaviors and to increase the risk of mortality by 3.2 times and decrease life spans from an average of 58 to 44 years at 11-year follow-up. Moreover, insulin misuse may be much more complex behavior than just the need for weight control. These behaviors may also involve increased distress, loss of control, and feelings of regret, guilt, and shame. Interestingly, most studies of eating disorders and type 1 diabetes use question regarding insulin omission as a surrogate marker for eating disorders and disordered eating. For instance, the question used in the BETTER registry are: "In the past 12 months, did you intentionally omit insulin injections with the objective of losing weight?" or "In a typical week, how often do you miss an insulin dose?". However, the validity and robustness of such a marker have not been specifically investigated yet. Our study objectives are : 1) To confirm that participants who reported intentionally omitting insulin had significantly more disordered eating behavior (based on the review of food records available); 2) To compare the prevalence and the severity of physical and mental health comorbidities (e.g., diabetes micro and macrovascular complications, glycated hemoglobin levels, current and past psychiatric disorders, distress related to diabetes) in people living with diabetes having or not declared to intentionally omit insulin; 3) To establish, using machine learning techniques, the main factors associated with intentional insulin omission behavior, taking into account biological, anthropometric and psychometric factors.

Our main hypotheses: 1. that people living with Type 1 diabetes who report intentional insulin omission will have a higher risk of disordered eating behaviors and diabetes-related comorbidities; 2. that it will be possible to establish different predictors of intentional insulin omissions behaviors by using machine learning techniques. Statistical Analysis: The normality of the data distribution will be checked for each value using a graphical analysis of the distribution and a Kolmogorov-Smirnov test before parametric tests are performed. A description of the characteristics of the participants included in this study will be performed. Continuous variables will be presented by the mean and standard deviation for normal distributions, median and range for others. Categorical variables will be presented by the number and percentage of each modality. The level of significance of the tests must be equal or lower than 0.05. The risk of alpha error is set at 0.05, with Bonferroni correction if necessary. * Objective 1 - 24-hour dietary recall: Macronutrients composition and repartition (in the day), as well as the serving sizes of the food intake will be calculated using the Canadian Food Guide 2007 or the Canadian Nutrient File. * Objective 2 - Prevalence and severity of diabetes and its comorbidities: Both groups, having or not intentionally omit insulin, will be compared using conventional statistical analyses. * Objective 3 - Predictive modeling: Based on a previous published methodology (Iceta et al., 2021), the first step will be to reduce entropy in the dataset using a ranking procedure (the Fast Correlation-Based Filter, FCBF) to identify the most discriminating predictor between the two class-labeled datasets (with and without insulin omission). Only items with an FCBF score \> 0.1 will be retained for the subsequent steps of the data-mining analysis. The second step of the data-mining analysis will aim at selecting the most relevant predictive algorithm for intentional insulin omission. Performances of different predictive algorithms will be tested and compared: logistic regression, artificial neural networks, naive Bayes classification, decision trees, AdaBoost meta-algorithm, CN2 rule inducer algorithm, SVM algorithm, k-nearest neighbors' algorithm and stochastic gradient algorithm. These artificial intelligence algorithms will be cross-validated (ten times in a row) with a randomized learning sample, renewed ten times and representing 66% of the study population. The validation sample will be represented by the other 33% of the population. The predictive algorithm with the best precision and F1 score will be considered as the best valuable algorithm.