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

Abstract

Background: Delivering insulin in type 1 diabetes is a challenging, and potentially risky, activity; hence the importance of including safety measures as part of any insulin dosing or recommender system. This work presents and clinically evaluates a modular safety system that is part of an intelligent insulin dose recommender platform developed within the EU-funded PEPPER project. Methods: The proposed safety system is composed of four modules which use a novel glucose forecasting algorithm. These modules are predictive glucose alerts and alarms; a predictive low-glucose basal insulin suspension module; an advanced rescue carbohydrate recommender for resolving hypoglycemia; and a personalized safety constraint applied to insulin recommendations. The technical feasibility of the proposed safety system was evaluated in a pilot study including eight adult subjects with type 1 diabetes on multiple daily injections over a duration of six weeks. Glycemic control and safety system functioning were compared between the two-weeks run-in period and the end point at eight weeks. A standard insulin bolus calculator was employed to recommend insulin doses. Results: Overall, glycemic control improved over the evaluated period. In particular, percentage time in the hypoglycemia range (<3.0 mmol/l) significantly decreased from 0.82% (0.05-4.79) at run-in to 0.33% (0.00-0.93) at endpoint ( P = .02). This was associated with a significant increase in percentage time in target range (3.9-10.0 mmol/l) from 52.8% (38.3-61.5) to 61.3% (47.5-71.7) ( P = .03). There was also a reduction in number of carbohydrate recommendations. Conclusion: A safety system for an insulin dose recommender has been proven to be a viable solution to reduce the number of adverse events associated to glucose control in type 1 diabetes.

Predicting Quality of Overnight Glycaemic Control in Type 1 Diabetes Using Binary Classifiers

“…For instance, typical a DSS consist of alerts notifying the user of potential future adverse events, such as hypoglycaemia and hyperglycaemia [8]. They might also suggest the administration of meal insulin boluses or corrective insulin boluses to mitigate hyperglycaemia [9,10,11], recommend the intake of carbohydrates (CHO) to tackle hypoglycaemia (rescue CHO) [12,13,14], or provide suggestions to prevent exercise-induced hypoglycaemia [15].…”

An Insulin Bolus Advisor for Type 1 Diabetes Using Deep Reinforcement Learning

“…Here we use a simple constraint during in silico validation: the action gain is limited to be greater than 1 if current BG enters hyperglycemia and less than 1 for hypoglycemia. In a clinic practice, more advanced constraints could be used, such as a interval arithmetic-based dynamic insulin constraint proposed by Liu et al [ 42 ]. During the fine-tuning, the data is collected with a form of transitions, i.e., a tuple of .…”

“…The use of smartphone applications in diabetes management has seen promising results [ 44 ]. Several projects aiming at enhanced glucose management have used CGM and smartphone applications, such as DiAs [ 45 ], PEPPER [ 42 ], ABC4D [ 8 ], and iAPS [ 46 ]. The proposed algorithm will also be evaluated as the insulin bolus advisor on a smartphone platform for T1D self-management during an upcoming clinical trial.…”

Practical Implementation of Diabetes Technology: Real‐World Use

“…The good news is that this at a very broad level, the particular ADS system under study, the Advisor Pro, seemed to agree with doctors as much as doctors agree with doctors. Feasibility studies of ADS in T1D have been promising (18,19); if results from largerscale, longer-duration studies demonstrate efficacy, the incorporation of these systems into diabetes practices promises to improve efficiency, care delivery, and outcomes.…”