Predicting disease risks from highly imbalanced data using random forest

Table 6 Statistical comparison of RF and boosting ROC curves, the lower the value the more significant the difference is

Disease	p value
Breast cancer	0.8057
Diabetes no complication	0.3293
Diabetes with/complication	0.6266
Hypertension	0.2
Coronary Atherosclerosis	0.2764
Peripheral Atherosclerosis	0.8203
Other Circulatory Diseases	0.566
Osteoporosis	0.908

ISSN: 1472-6947