Skip to main content
. 2015 Jan 21;16(Suppl 1):S5. doi: 10.1186/1471-2105-16-S1-S5

Table 2.

Performance of utilizing variable numbers of clinical features in different classifiers to predict diabetic nephropathy.

Classifier No. of features Accuracy (%) Sensitivity (%) Specificity (%)
Decision tree 7 62.17 55.56 69.02
Random forest 6 63.91 60.68 67.26
SVM 3 60.87 50 78.72
Naïve Bayes 7 62.61 41.03 84.96