Title :
A probabilistic rule extraction method for an insulin advice algorithm for type 1 diabetes mellitus
Author :
McCausland, Lucia ; Y. Mareels, Iven
Author_Institution :
Dept. of Electr. & Electron. Eng., Melbourne Univ., Parkville, Vic., Australia
Abstract :
Type 1 diabetics make decisions on insulin doses given certain conditions, such as blood glucose levels, food and exercise, every day of their lives, using a set of rules. The complex nature of the disease and the limited amount of data available have posed challenges in establishing such rules for an advisory expert system. The authors address the issues surrounding selecting techniques which are most appropriate to extract and update these rules
Keywords :
adaptive control; biocontrol; diseases; medical expert systems; organic compounds; probability; advisory expert system; blood glucose levels; exercise; food; insulin advice algorithm; insulin doses decisions; probabilistic rule extraction method; rules extraction; rules updating; type 1 diabetes mellitus; Adaptive control; Blood; Control systems; Data mining; Diabetes; Diseases; Expert systems; Insulin; Sections; Sugar;
Conference_Titel :
Engineering in Medicine and Biology Society, 2000. Proceedings of the 22nd Annual International Conference of the IEEE
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-6465-1
DOI :
10.1109/IEMBS.2000.900820