A Modular Safety System for an Insulin Dose Recommender: A Feasibility Study.

Area of Science:

• Endocrinology
• Biomedical Engineering
• Diabetes Technology

Background:

• Insulin delivery in type 1 diabetes presents significant safety challenges.
• The EU-funded PEPPER project developed an intelligent insulin dose recommender platform.
• Integrating robust safety measures is crucial for insulin dosing systems.

Purpose of the Study:

• To present and clinically evaluate a modular safety system for an intelligent insulin dose recommender.
• To assess the system's impact on glycemic control and safety in type 1 diabetes patients.
• To demonstrate the feasibility of a predictive safety system for insulin therapy.

Main Methods:

• A modular safety system comprising four modules was developed, utilizing a novel glucose forecasting algorithm.
• Modules included predictive glucose alerts, basal insulin suspension for hypoglycemia, carbohydrate recommendations, and personalized safety constraints.
• A pilot study involved eight adults with type 1 diabetes over eight weeks, comparing a run-in period with the safety system's endpoint, using a standard insulin bolus calculator.

Main Results:

• Glycemic control improved significantly over the study period.
• Percentage time in hypoglycemia (<3.0 mmol/l) decreased from 0.82% to 0.33% (P = .02).
• Percentage time in target range (3.9-10.0 mmol/l) increased from 52.8% to 61.3% (P = .03), with fewer carbohydrate recommendations.

Conclusions:

• A safety system integrated with an insulin dose recommender is a viable solution.
• The system effectively reduces adverse events related to glucose control in type 1 diabetes.
• Clinical evaluation demonstrated improved glycemic control and enhanced safety for insulin therapy.