PP439 Data Driven Subgroups Of Patients With Type 1 Diabetes Based On Health Technology For Insulin Delivery

Abstract

IntroductionPatients with type 1 diabetes (T1D) require the administration of insulin to maintain glycemic control. Currently, two modes of subcutaneous insulin delivery have gained wider acceptance: multiple daily injections (MDI) and continuous subcutaneous insulin infusion (CSII). Randomized controlled trials have shown that CSII is associated with a slightly lower glycated hemoglobin (HbA1c) level when compared with MDI.The case study on diabetes by the H2020 Next Generation Health Technology Assessment project aims to link evidence from randomized controlled trials to real-world data to estimate the impact of health technology on specific subgroups of patients, as a first step in building prediction models to personalize treatment strategies. This work aims to assess whether patients with T1D can be stratified according to the use of health technology for insulin delivery and associated glycemic control from real-world data.MethodsWe used a longitudinal prospective data repository of T1D patients from 83 clinics in the United States (T1D exchange). A data-driven two-step clustering analysis was done on adult individuals (n = 8,034) with more than five years of disease duration. Clusters were based on body mass index (BMI), sex, age at diagnosis, diabetes duration, HbA1c level, and insulin delivery method. The optimal number of clusters was estimated based on silhouette width.ResultsWe identified the following four clusters of T1D patients characterized by differences in gender and insulin delivery method: men and women with insulin injections or pens and men and women with CSII. Individuals that used CSII had lower HbA1c levels, a higher BMI, and longer diabetes duration than those using Injections or pens.ConclusionsThis preliminary work identified subgroups of T1D patients linked to insulin delivery methods. Future research includes the study of complications associated with different clusters and additional data sources. While the data were sourced from the T1D Exchange, the analyses, content, and conclusions presented have not been reviewed or approved by the T1D Exchange.