Diabetes Therapy Prognosis through Data Stream Mining Methods and Technologies

Dana Wang, Simon Fong, Seoungjae Cho, Kyungeun Cho, and Yongwoon Park

Keywords

Diabetes therapy, Insulin mellitus, Classification algorithms, Data stream mining

Abstract

Diabetes is one of the frequently occurring non-communicable diseases that lead causes of deaths among the worldwide. Maintain an appropriate blood glucose value for the patient needs a right amount of insulin dosage and the timing of its intake. But the medical interaction to the different lifestyle patients cause to the complexity of the therapy. In this article, a real-time classification therapy prognosis model is proposed to compute for regulating IDDM based on the daily prescription record and patients’ individual blood glucose pattern by using data stream mining. A computer simulation is presented for evaluating the most appropriate data stream algorithms for this task.

Important Links:



Go Back


IASTED
Rotating Call For Paper Image