MELISSA Projekt MobilE artificiaL Intelligence Solution for DiabeteS Adapted care

Achieving near-normal glycaemic control remains to be challenging for the vast majority of people with type 1 or type 2 diabetes on intensive insulin treatment, despite advances in insulin delivery and glucose monitoring technology over the past decades. Daily insulin requirements of people with diabetes are dynamic due to major influence of known factors such as carbohydrate intake, physical activity, concurrent health conditions and various unknown factors including mood and variability in insulin absorption. While the effect of some of the known factors can partly be mitigated by the patients adjusting their daily insulin dosing, the effect of other (known and unknown) factors remain an obstacle to achievement of optimal glycaemic control and quality of life due to hyper- and hypoglycaemic excursions resulting from ‘erroneous’ insulin dosing. Consequently, many patients with diabetes do not reach recommended glycaemic targets and remain at increased risk of developing devastating late-diabetic complications. At present, systems for decision support with regards to daily insulin dosing for patients treated with Multiple Daily Injections (MDI) are limited to the coverage of basal insulin requirements and to simple bolus calculators of meal-related insulin administration working with fixed algorithms based on carbohydrate intake, correction factors and insulin on board. Enhancement of algorithms by Artificial Intelligence (AI) may have a considerable potential to further qualify daily decision-making for many people with diabetes by compensating for the effect of factors, which are not manageable to the patient, affecting the insulin need. Preliminary work based on in-silico simulations (preclinical validation) has shown that the AI-powered adaptive basal bolus algorithm in the MELISSA platform considerably improved glycaemic outcomes of people with already reasonably-well controlled type 1 diabetes.

The proposed MELISSA project entails a large-scale randomised controlled clinical trial conducted in several European countries. The primary objective of the MELISSA study is to demonstrate superiority of glycaemic control as compared to the standard(s) of care not using AI-powered decision making with the primary endpoint being improvement of time-in-range and a range of clinically relevant secondary endpoints.