Latent Class Analysis of Noninvasive Methods and Liver Biopsy in Chronic Hepatitis C: An Approach without a Gold Standard

Table 3

Competitive comparison of latent classes models for assessment of liver fibrosis by noninvasive methods [TE, APRI, and ELF] and liver biopsy.

Model	Model specification	Significant fibrosis ()		Cirrhosis ()
		( value)	BIC	( value)
2LC		9.9504 (0.1268)		5.6494 (0.4636)
2LC with direct effect between TE and APRI		7.9601 (0.0931)		4.7289 (0.3163)
2LC with direct effect between TE and ELF		7.9397 (0.0938)		5.4854 (0.2410)
2LC with direct effect between APRI and ELF		6.2539 (0.1810)		0.1466 (0.9988)

LC, latent class; , likelihood squared; BIC, Bayesian information criterion; TE, transient elastography; APRI, aspartate-to-platelet-ratio-index; ELF, enhanced liver fibrosis. 2LC was the model that data better fits for estimation of significant fibrosis and cirrhosis.