Interactive Pancreas, Digital Twins Boost Diabetes Control

New advancements in technology have enabled a University of Virginia-developed artificial pancreas system to adapt to users’ changing needs, significantly improving management of type 1 diabetes. A recent study highlights that this innovative system, equipped with Adaptive Biobehavioral Control (ABC) technology, allows users to experiment with system operations and optimize insulin delivery.

The ABC technology fine-tunes the automated insulin delivery system within the artificial pancreas biweekly, while providing users with a “digital twin”—a computer simulation to explore different methods of blood sugar management. Results from this six-month study revealed that participants utilizing this technology increased the time they spent in a safe blood-sugar range from 72% to 77%, and reduced their hemoglobin A1c levels from 6.8% to 6.6%.

“Artificial pancreas systems require continuous adjustment by users to accommodate varying insulin demands,” explained Boris Kovatchev, PhD, director of the UVA Center for Diabetes Technology. “This is the first study mapping each individual to their ‘digital twin’ in the cloud. It empowers people with diabetes to safely learn and experiment with their own data, understanding how their artificial pancreas might react to changes within a simulation environment before committing to actual adjustments.”

A ‘Digital Twin’ for Diabetes Control

Automated insulin delivery systems like the artificial pancreas have been instrumental in helping users control type 1 diabetes. However, ABC technology addresses two pervasive challenges. The first is enhancing blood-sugar control during daytime when events such as meals and exercise can cause fluctuations. Secondly, while users initially thrive by spending more time in the safe blood-sugar range, they often hit a plateau, typically between 70% to 75%, which researchers speculate is due to the difficulty of adapting to the system’s performance.

ABC technology tackles these challenges through “digital twins,” which are computerized simulations that mirror users’ metabolic systems. Not only do these twins optimize the artificial pancreas in response to shifts in physiology and behavior, but they also allow users to simulate adjustments. For instance, users can test altering the continuous overnight insulin delivery from their pumps.

“Human-machine co-adaptation is essential for conditions like type 1 diabetes, where treatment decisions involve both the artificial pancreas algorithm and the user. Digital-twin technology is particularly beneficial in promoting this co-adaptation,” Kovatchev emphasized.

Results Published

The team of researchers, comprising Kovatchev, Patricio Colmegna, Jacopo Pavan, Jenny L. Diaz Castañeda, Maria F. Villa-Tamayo, Chaitanya L. K. Koravi, Giulio Santini, Carlene Alix, Meaghan Stumpf, and Sue A. Brown, have published their findings in the journal npj Digital Medicine. The study was supported by grant RO1 DK085623 from the National Institute of Diabetes and Digestive and Kidney Diseases. A comprehensive list of author disclosures is included within the published paper.

For those interested in remaining informed on the latest in medical research from UVA, subscribing to the Making of Medicine blog is highly recommended.

Public Release: This material from the originating organization/author(s) could represent a point-in-time perspective, and has been edited for clarity, style, and length. Mirage.News maintains neutrality, and all opinions, positions, and conclusions expressed are exclusively those of the author(s).

Leave a Reply

Your email address will not be published. Required fields are marked *

You May Also Like

Unveiling Oracle’s AI Enhancements: A Leap Forward in Logistics and Database Management

Oracle Unveils Cutting-Edge AI Enhancements at Oracle Cloud World Mumbai In an…

Charting New Terrain: Physical Reservoir Computing and the Future of AI

Beyond Electricity: Exploring AI through Physical Reservoir Computing In an era where…

Challenging AI Boundaries: Yann LeCun on Limitations and Potentials of Large Language Models

Exploring the Boundaries of AI: Yann LeCun’s Perspective on the Limitations of…

TECNO CAMON 30 Series: Exploring Advanced AI Innovations in Smartphone Technology

TECNO CAMON 30 Series: A New Era of Smartphones Embellished with Advanced…