Table 3.

The comparison of sensitivity between CA-125 alone and all four proteins (CA-125, MIF, OPN, and PROL) when using the four classification techniques. The sensitivity measures the ability to correctly identify condition samples and is defined as the ratio of the number of condition samples correctly classified to the total number of condition samples. We highlighted the cell(s) with best sensitivity in each experiment. Using random forest and all four proteins yield the best results on most occasions.

ID	Training	Testing	CA-125					4 Proteins
			KNN	LR	RF	SVM	Mean	KNN	LR	RF	SVM	Mean
1	E1 vs. H1	E1 vs. H1	0.71	0.86	0.71	0.71	0.75	0.86	0.57	1	0.71	0.79
2	E1 vs. H1	E2 vs. H2	0.58	0.63	0.58	0.47	0.57	0.68	0.58	0.74	0.47	0.62
3	E1 vs. H1	C2 vs. H2	0.55	0.56	0.59	0.49	0.55	0.50	0.42	0.63	0.66	0.55
4	L1 vs. H1	L1 vs. H1	0.77	0.91	0.92	0.77	0.84	1	1	1	1	1.00
5	L1 vs. H1	L2 vs. H2	0.66	0.66	0.66	0.62	0.65	0.69	0.74	0.75	0.74	0.73
6	L1 vs. H1	C2 vs. H2	0.66	0.65	0.65	0.59	0.64	0.70	0.76	0.78	0.76	0.75
7	C1 vs. H1	E2 vs. H2	0.79	0.74	0.63	0.68	0.71	0.84	0.89	0.89	0.89	0.88
8	C1 vs. H1	L2 vs. H2	0.72	0.67	0.67	0.64	0.68	0.69	0.74	0.75	0.74	0.73
9	C1 vs. H1	C2 vs. H2	0.74	0.70	0.69	0.64	0.69	0.73	0.76	0.76	0.76	0.75
10	E2 vs. H2	E2 vs. H2	0.14	0.14	0.14	0.14	0.14	0.29	0.57	0.43	0.29	0.40
11	E2 vs. H2	E1 vs. H1	0.28	0.22	0.33	0.22	0.26	0.67	0.83	0.89	0.83	0.81
12	E2 vs. H2	C1 vs. H1	0.38	0.36	0.42	0.37	0.38	0.33	0.52	0.58	0.68	0.53
13	L2 vs. H2	L2 vs. H2	0.54	0.46	0.58	0.46	0.51	0.67	0.67	0.71	0.67	0.68
14	L2 vs. H2	L1 vs. H1	0.78	0.78	0.76	0.76	0.77	0.89	0.87	0.95	0.87	0.90
15	L2 vs. H2	C1 vs. H1	0.73	0.70	0.71	0.68	0.71	0.89	0.81	0.93	0.86	0.87
16	C2 vs. H2	E1 vs. H1	0.67	0.61	0.72	0.56	0.64	0.94	0.94	0.94	0.94	0.94
17	C2 vs. H2	L1 vs. H1	0.76	0.76	0.78	0.75	0.76	0.87	0.87	0.93	0.87	0.89
18	C2 vs. H2	C1 vs. H1	0.71	0.70	0.77	0.67	0.71	0.89	0.90	0.92	0.88	0.90