Real-Life Use of Automated Insulin Delivery in Individuals With Type 2 Diabetes

Abstract

Background: The objective of this work is to document performance of automated insulin delivery (AID) during real-life use in type 2 diabetes (T2D).

Methods: A retrospective analysis was performed of continuous glucose monitoring and insulin delivery data from 796 individuals with T2D, who transitioned from 1-month predictive low-glucose suspend (PLGS) use to 3-month AID use, in real-life settings. Primary outcome was change of time in range (TIR = 70-180 mg/dL) from PLGS to AID. Secondary outcomes included time above/below range (TAR/TBR) and total daily insulin (TDI).

Results: Compared with PLGS, AID increased TIR on average from 63.2% to 72.6%, decreased TAR from 36.2% to 26.8%, and increased TDI from 70.2 to 76.3 U (all P < .001), without significant change to TBR. Glycemic improvements were more pronounced in those with worse glycemic control during PLGS use (P < .001).

Conclusions: Real-life use of AID led to a rapid and sustained improvement of glycemic control in individuals with T2D.

Keywords: automated insulin delivery; continuous glucose monitoring; insulin pump; real life; time in range; type 2 diabetes.

Figure 1.

Evolution of the percent time spent in 70 to 180 mg/dL (left) and total daily insulin (right), as technology users transition from predictive low-glucose suspend (PLGS) use to automated insulin delivery (AID) use. Day 0 is the day of system transition. Each panel displays four user groups each referring to a different baseline (ie, during PLGS use) glucose management indicator (GMI_PLGS) range, per figure legend, with the following number of users in each group: 219 (blue), 250 (purple), 193 (red), and 134 (yellow). Continuous lines are metric averages across subjects for each day of analysis; shaded areas are 95% confidence intervals.