Table 3 SOML algorithms

	Model^a	A	B	C	D	E	F	G
	# of Glycoforms^b	7	12	15	3	12	5	39
	Clinical factors^c	Age, AFP	Age, AFP	Age, AFP	Age, AFP	Age, AFP	Age, AFP	Age, AFP, Gender
AP^d	AUC^e	0.90	0.92	0.93	0.88	0.92	0.90	0.97
	SE^f	0.02	0.02	0.02	0.02	0.02	0.02	0.02
	95% CI-LL^g	0.86	0.88	0.90	0.83	0.89	0.85	0.94
	95% CI-UL^h	0.95	0.96	0.97	0.93	0.96	0.94	1.0
5-fold CVⁱ	Mean	0.89	0.89	0.91	0.87	0.91	0.88	0.91
	SE	0.04	0.06	0.04	0.05	0.04	0.05	0.05
	Max	0.98	0.98	0.99	0.97	1.0	0.96	1.0
	Min	0.76	0.76	0.76	0.73	0.78	0.74	0.77

^aSeven diagnostic algorithms were created using a support vector machine with a linear kernel.
^bThe number of glycoforms (proteins with unique glycans in each model).
^cClinical factors such as age, AFP, or gender are used in model.
^dAP, apparent validation.
^eArea under the curve for each model for apparent validation.
^fSE, standard error.
^g95%CI-LL, lower limit of 95% confidence interval.
^h95%CI-UL, upper limit of 95% confidence interval.
ⁱ5-fold CV, fivefold cross-validation.

Quick links

Search