Abstract
Metaheuristic search algorithms are used to develop new protocols for optimal intravenous insulin infusion rate recommendations in scenarios involving hospital in-patients with Type 1 Diabetes. Two metaheuristic search algorithms are used, namely, Particle Swarm Optimization and Covariance Matrix Adaption Evolution Strategy. The Glucose Regulation for Intensive Care Patients (GRIP) serves as the starting point of the optimization process. We base our experiments on a methodology in the literature to evaluate the favorability of insulin protocols, with a dataset of blood glucose level/insulin infusion rate time series records from 16 patients obtained from the Waikato District Health Board. New and significantly better insulin infusion strategies than GRIP are discovered from the data through metaheuristic search. The newly discovered strategies are further validated and show good performance against various competitive benchmarks using a virtual patient simulator.
Highlights
Diabetes is a fast-growing global problem.[1]
Our research aims to develop and optimize algorithm-based insulin infusion protocols for in-patients instead of ICU patients, the ICU-based insulin infusion protocols provide nice comparison and some of them can act as starting points for AI optimization
The recommended insulin infusion rate is computed as the product of the current multiplier and the current blood glucose level o®set by a constant
Summary
Diabetes is a fast-growing global problem.[1]. It is caused by the body's inability to produce insulin or due to body's resistance to insulin. Patients admitted to our local hospital due to diabetes are subjected to continuous intravenous insulin infusion therapy The goal of such therapy is to keep the blood glucose levels of the patient in a dened normal range (usually 6–10 mmol/L). The novel contribution of our research is twofold It shows that metaheuristic search algorithms can be used to optimize the parameters of GRIP, improving and adopting the strategy with respect to the historical data. Newly discovered strategies can be validated using simulated virtual patients, who have never been exposed to the optimization process, and exhibit better performance than both GRIP, which is the base of the optimization, and the current local hospital practice, which is the historical protocol used to produce the data for optimization. This paper includes more detail than Ref. 5, e.g. more detailed illustration of optimization results and more comprehensive background on insulin infusion protocols
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
