82-LB: Improvement of Glycemic Control in People with Type 2 Diabetes Using Basal Insulin (PwT2D-BI) and Continuous Glucose Monitoring (CGM) —U.S. Study Using Machine Learning (ML)

Abstract

Background: CGM provide real-time glucose data that allows users to manage their diabetes holistically. This study aimed to assess the association between glycemic control and CGM use in PwT2D-BI. Methods: This retrospective study used IBM MarketScan® 2015 - 2019 Databases to identify PwT2D-BI with (CGM) and without (control) use of CGM. CGM users were followed from first BI until CGM initiation, defined as index date (ID) . The ID of non-CGM controls were randomly assigned based on time between first BI and ID of CGM. . Comparison CGM use for 6 and 12 months were performed using Frequentist Model Averaging (FMA) in a ML framework adjusting for baseline characteristics. Model strategies were applied including matching, weighting, stratification and regression. Results: A total of 5,934 PwT2D-BI (251 CGM; 5,683 control) were included in the study (Table 1) . Observed A1c reduction from baseline to 12 months was 0.87%, 0.95% for 6 and 12 months of CGM use, respectively vs. 0.32% for controls. FMA analyses found CGM users had a statistically significantly greater reduction in A1c both at 6 months (treatment difference 0.30 [0.13,0.48]) and 12 months (0.50 [0.37, 0.72]) . Conclusion: Findings suggest that CGM use for at least 6 months in PwT2D-BI has clinical benefit as demonstrated by A1c reduction in the real-world setting. Disclosure C. Chinthammit: Employee; Eli Lilly and Company, Stock/Shareholder; Eli Lilly and Company. A. J. M. Brnabic: Employee; Eli Lilly and Company, Stock/Shareholder; Eli Lilly and Company. M. Perez-nieves: Employee; Eli Lilly and Company, Stock/Shareholder; Eli Lilly and Company. Funding Eli Lilly and Company