Mitigation of hypoglycemia during Ramadan using the flash glucose monitoring system following dose adjustment of insulin and sulphonylurea in patients taking multiple glucose-lowering therapies (The PROFAST-IT Study).

BACKGROUND AND HYPOTHESIS: Patients with type-2 diabetes mellitus (T2DM) on multiple glucose-lowering therapies who fast during Ramadan are at increased risk of hypoglycemia. We have assessed the utility of the flash glucose monitoring system after adjusting the dose of insulin and sulphonylureas to mitigate the risk of hypoglycemia in patients with T2DM who fast during Ramadan. PATIENTS AND METHODS: Patients with T2DM on either basal insulin or a sulphonylurea and at least 2 other glucose-lowering agents received structured education and adjustment of insulin or sulphonylurea dose according to the PROFAST Ramadan protocol. Glucose variability and episodes of hypoglycemia were assessed using the flash glucose monitoring system (Free Style Libre) before and during Ramadan. RESULTS: A total of 33 patients with T2DM (on sulphonylurea (SU+) (n = 21), on basal insulin (BI+) (n = 12) aged 50.8 ± 1.6 years with a diabetes duration of 13.1 ± 6.5 years were studied. The average sensor glucose was 154 ± 34 mg/dl (8.5 ± 1.88 mmol/l) with 65.2% in the target range before Ramadan and the average sensor glucose was 156 ± 36 mg/dl (8.6 ± 2.0 mmol/l) with 67.1% in the target range during Ramadan. The incidence of hypoglycemia in the whole group (2.9 v 2.9) and in the SU+ (3.7 vs 3.0) and BI+ (1.7 vs 2.9) groups and eHbA1c (P = 0.56, P = 0.93), average glucose (P = 0.56, P = 0.92) and time within range (P = 0.63, P = 0.73) did not change in the SU+ and BI+ groups, respectively, before and during Ramadan. CONCLUSION: Structured education with adjustment of the dose of glucose lowering medication alongside use of the FGMS can effectively mitigate the increased risk of hypoglycemia in patients with T2DM on multiple glucose-lowering therapies who fast during Ramadan.

Artificial Intelligence (AI) based machine learning models predict glucose variability and hypoglycaemia risk in patients with type 2 diabetes on a multiple drug regimen who fast during ramadan (The PROFAST - IT Ramadan study).

OBJECTIVE: To develop a machine-based algorithm from clinical and demographic data, physical activity and glucose variability to predict hyperglycaemic and hypoglycaemic excursions in patients with type 2 diabetes on multiple glucose lowering therapies who fast during Ramadan. PATIENTS AND METHODS: Thirteen patients (10 males and three females) with type 2 diabetes on 3 or more anti-diabetic medications were studied with a Fitbit-2 pedometer device and Freestyle Libre (Abbott Diagnostics) 2 weeks before and 2 weeks during Ramadan. Several machine learning techniques were trained to predict blood glucose levels in a regression framework utilising physical activity and contemporaneous blood glucose levels, comparing Ramadan to non-Ramadan days. RESULTS: The median age of participants was 51 years (IQR 49-52); median BMI was 33.2 kg/m2 (IQR 33.0-35.9) and median HbA1c was 7.3% (IQR 6.7-7.8). The optimal model using physical activity achieved an R2 of 0.548 and a mean absolute error (MAE) of 30.30. The addition of electronic health record (ehr) information increased R2 to 0.636 and reduced MAE to 26.89 and the time of the day feature further increased R2 to 0.768 and reduced MAE to 20.55. Combining all the features together resulted in an optimal XGBoost model with an R2 of 0.836 and MAE of 17.47. This model accurately estimated normal glucose levels in 2584/2715 (95.2%) readings and hyperglycaemic events in 852/1031 (82.6%) readings, but fewer hypoglycaemic events (48/172 (27.9%)). The optimal XGBoost model prioritized age, gender, BMI and HbA1c followed by glucose levels and physical activity. Interestingly, the blood glucose level prediction by our model was influenced by use of SGLT2i. CONCLUSION: XGBoost, a machine learning AI algorithm achieves high predictive performance for normal and hyperglycaemic excursions, but has limited predictive value for hypoglycaemia in patients on multiple therapies who fast during Ramadan.