abc4d

Role: Development of the ABC4D server and deployment on AWS.

The recent increase in the use of technologies such as continuous glucose monitoring (CGM) and self-management mobile apps has led to a digital transformation in diabetes care. However, despite the increasing adoption of these technologies, fewer than one-third of people with Type 1 diabetes achieve their glycaemic targets. Hence, there is an urgent need to empower people living with diabetes with intelligent software tools that can automatically analyse and systematically provide safe, personalized, and effective therapeutic recommendations.

Insulin bolus calculators have been developed to aid insulin dose adjustment and are currently incorporated in most of the latest commercially available insulin pumps and some glucose meters. Although effective to some degree, they still fall short in achieving glycemic therapeutic targets due to the high variability in diabetes management.

At the Centre for Bio-inspired Technology, we have developed an Advanced Bolus Calculator for Diabetes (ABC4D) that uses continuous glucose monitoring (CGM), Run-to-Run control, and the artificial intelligence technique of Case-based Reasoning (CBR) to overcome these barriers.

The developed insulin recommendation algorithm has been implemented within a mobile app that communicates in real-time with a continuous glucose sensor and requires the user to manually input meals, and physical exercise information to calculate a recommended insulin dose that is tailored to the individual and the current circumstances. The algorithm also adapts its recommendation based on the outcomes of past recommended insulin doses and user behavior.

Posts

• Featured in the CBIT newsletter

Publications