Advanced Bolus Calculator for Diabetes (ABC4D)
Type 1 diabetes is a chronic disease resulting in elevated blood glucose concentrations, which, if not managed, increases the risk of cardiovascular problems and can lead to blindness, kidney failure, and nerve damage. The standard treatment involves multiple daily injections of insulin to lower blood sugar levels accordingly. In order to calculate the right amount of insulin, simple bolus calculators exist, but often do not consider enough parameters to be effective and are not personalised. This research focuses on intelligent systems that help people with diabetes managing their blood glucose levels, thus reducing aforementioned long term complications and improving the quality of life of patients.
This work analyses how various human and environmental factors, such as exercise, stress and alcohol consumption, influence blood glucose levels and how these parameters can be incorporated in intelligent decision support systems (DSS). One application of DSS in diabetes management is to provide recommendations for the amount of bolus insulin that is being administered when eating a meal.Our current DSS is built on Case-Based Reasoning, an artificial intelligence technique that learns over time based on past experiences and therefore is individualised for each patient. This has been fully integrated into a smatphone plaftorm for every day use by people suffering from diabetes.
Imperial College has an active study on the evaluation of an Advanced Bolus Calculator for Diabetes (ABC4D). More information at: http://clinicaltrials.gov/ct2/show/NCT02053051
- Herrero P., Pesl P., Reddy M., Oliver N., Georgiou P., and Toumazou C. Advanced Insulin Bolus Advisor based on Run-To-Run Control and Case-Based Reasoning. IEEE J Biomed Health Inform, 2014 (In Press).
- Herrero P., Pesl P., Bondia J., Reddy M., Oliver N., Georgiou P., Toumazou C. Method for automatic adjustment of an insulin bolus calculator: In silico robustness evaluation under intra-day variability. Computer Methods and Programs in Biomedicine, 2015 (In Press).