Evaluation of Stream Mining Classifiers for Real-Time Clinical Decision Support System: A Case Study of Blood Glucose Prediction in Diabetes Therapy

Table 2

Results of the accuracy test.

Accuracy	VFDT	iOVFDT	Bayes	Perceptron
Mean	87.4314%	86.4102%	82.6453%	25.4779%
Max	95.6810%	93.7930%	95.1720%	91.6670%
Min	78.8460%	79.3100%	25.3010%	0.0000%
Std. dev.	0.0403	0.0342	0.1184	0.3164
Quartiles 25	85.4633	84.4560	81.5950	0.0000
Quartiles 50	87.3395	86.1990	85.6170	11.4720
Quartiles 75	90.2530	89.0150	88.4955	53.8140