Fully Automating AID Systems for Insulin Delivery Would Help Diabetes Patients, Research Finds

Many AID systems, like an artificial pancreas, still require user input of meals and exercises.

A new review of automated insulin delivery (AID) systems found that the devices “could help more type 1 diabetes patients if [they] become fully automated.”

AID systems like the artificial pancreas have helped people with type 1 diabetes “better manage their blood sugar and improve their overall health,” but the devices still have limitations. The systems are “not yet fully automated,” meaning “users must input their meals and exercise to avoid dangerous spikes or drops in blood-sugar levels;” the devices “work best overnight;” and they are “not yet usable by all patients with type 1 diabetes, including women who are pregnant and older adults.”

The researchers wrote that a key goal for AID systems is to fully automate them so they require “less or no interaction.” Researchers at the UVA Center for Diabetes are “conducting home-based clinical trials testing a system that merges artificial intelligence and advanced model-based algorithms to deliver insulin around meals independently of any user-machine interactions.”

Other institutions are working on developing “artificial intelligence approaches that automatically detect meals and deliver corresponding insulin doses.”

About the Author

Matt MacKenzie

Matt MacKenzie

Associate Editor

Matt MacKenzie is Senior Staff Writer and Associate Editor of Healthcare Purchasing News (HPN), where he leads daily news coverage and contributes in-depth features on healthcare supply chain, sterile processing, infection prevention and clinical operations. Through industry reporting and expert interviews, he examines the trends, technologies and operational challenges shaping healthcare purchasing and patient care. 

Sign up for our eNewsletters
Get the latest news and updates