Closed-loop insulin delivery in suboptimally controlled type 1 diabetes: a multicentre, 12-week randomised trial

Abstract

Background: The achievement of glycaemic control remains challenging for patients with type 1 diabetes. We assessed the effectiveness of day-and-night hybrid closed-loop insulin delivery compared with sensor-augmented pump therapy in people with suboptimally controlled type 1 diabetes aged 6 years and older.

Methods: In this open-label, multicentre, multinational, single-period, parallel randomised controlled trial, participants were recruited from diabetes outpatient clinics at four hospitals in the UK and two centres in the USA. We randomly assigned participants with type 1 diabetes aged 6 years and older treated with insulin pump and with suboptimal glycaemic control (glycated haemoglobin [HbA_1c] 7·5-10·0%) to receive either hybrid closed-loop therapy or sensor-augmented pump therapy over 12 weeks of free living. Training on study insulin pump and continuous glucose monitoring took place over a 4-week run-in period. Eligible subjects were randomly assigned using central randomisation software. Allocation to the two study groups was unblinded, and randomisation was stratified within centre by low (<8·5%) or high (≥8·5%) HbA_1c. The primary endpoint was the proportion of time that glucose concentration was within the target range of 3·9-10·0 mmol/L at 12 weeks post randomisation. Analyses of primary outcome and safety measures were done in all randomised patients. The trial is registered with ClinicalTrials.gov, number NCT02523131, and is closed to accrual.

Findings: From May 12, 2016, to Nov 17, 2017, 114 individuals were screened, and 86 eligible patients were randomly assigned to receive hybrid closed-loop therapy (n=46) or sensor-augmented pump therapy (n=40; control group). The proportion of time that glucose concentration was within the target range was significantly higher in the closed-loop group (65%, SD 8) compared with the control group (54%, SD 9; mean difference in change 10·8 percentage points, 95% CI 8·2 to 13·5; p<0·0001). In the closed-loop group, HbA_1c was reduced from a screening value of 8·3% (SD 0·6) to 8·0% (SD 0·6) after the 4-week run-in, and to 7·4% (SD 0·6) after the 12-week intervention period. In the control group, the HbA_1c values were 8·2% (SD 0·5) at screening, 7·8% (SD 0·6) after run-in, and 7·7% (SD 0·5) after intervention; reductions in HbA_1c percentages were significantly greater in the closed-loop group compared with the control group (mean difference in change 0·36%, 95% CI 0·19 to 0·53; p<0·0001). The time spent with glucose concentrations below 3·9 mmol/L (mean difference in change -0·83 percentage points, -1·40 to -0·16; p=0·0013) and above 10·0 mmol/L (mean difference in change -10·3 percentage points, -13·2 to -7·5; p<0·0001) was shorter in the closed-loop group than the control group. The coefficient of variation of sensor-measured glucose was not different between interventions (mean difference in change -0·4%, 95% CI -1·4% to 0·7%; p=0·50). Similarly, total daily insulin dose was not different (mean difference in change 0·031 U/kg per day, 95% CI -0·005 to 0·067; p=0·09) and bodyweight did not differ (mean difference in change 0·68 kg, 95% CI -0·34 to 1·69; p=0·19). No severe hypoglycaemia occurred. One diabetic ketoacidosis occurred in the closed-loop group due to infusion set failure. Two participants in each study group had significant hyperglycaemia, and there were 13 other adverse events in the closed-loop group and three in the control group.

Interpretation: Hybrid closed-loop insulin delivery improves glucose control while reducing the risk of hypoglycaemia across a wide age range in patients with suboptimally controlled type 1 diabetes.

Funding: JDRF, NIHR, and Wellcome Trust.

Figure 1

Trial profile *One patient had two severe hypoglycaemia events during run-in.

Figure 2

Sensor glucose Median (IQR) concentrations in the closed-loop group (red line and shaded area; n=46) and the control group (blue line and shaded area; n=40) are shown. Dashed lines indicate the target glucose range (3·9–10·0 mmol/L).

Figure 3

Cumulative distribution of percentage of time that sensor glucose was within the target range (ie, 3·9–10·0 mmol/L) over 12-week intervention phase by treatment group