An Intelligent Diagnostic System to Analyze Early-Stage Chronic Kidney Disease for Clinical Application

Table 6

Experimental result analysis of various classifiers for with and without PCA on dataset-1 (CKD-15).

Classifier	Recall		TNR		PPV		F1-score		Train accuracy		Test accuracy		ROC-AUC
	With PCA	Without PCA	With PCA	Without PCA	With PCA	Without PCA	With PCA	Without PCA	With PCA	Without PCA	With PCA	Without PCA	With PCA	Without PCA
ADAB	100	100	100	100	100	100	100	100	100	100	100	100	1	1
DT	100	100	100	100	100	100	100	100	100	100	100	100	1	1
ELM	100	88	100	100	100	100	100	94	100	96	100	94.04	1	0.990
GB	100	99	100	100	100	100	100	99	100	99.72	100	99.34	1	0.993
KNN	100	43	100	97	100	94	100	59	100	76.99	100	70.2	1	0.7
LR	100	95	100	96	100	96	100	95	100	93.75	100	95.36	1	0.985
MLP	100	88	100	97	100	97	100	92	100	94.03	100	92.72	1	0.927
PAC	100	83	100	25	100	52	100	64	100	58.24	100	53.64	1	0.540
RF	100	100	100	100	100	100	100	100	100	100	100	100	1	1
SGD	100	48	100	99	100	97	100	64	100	77.84	100	73.51	1	0.748
SVM	100	43	100	83	100	71	100	54	100	60.8	100	62.91	1	0.628
NB	92	88	100	100	100	100	96	94	97.16	96.31	96.03	94.04	0.991	1

The best results are indicated in bold.