A detailed analysis of the Knodell score and other histologic parameters as predictors of response to interferon therapy in chronic hepatitis C

Abstract

The Knodell score is inaccurate at predicting response to interferon alpha (IFN-alpha) therapy in patients with hepatitis C. Our aim was to see if specific histologic parameters, including iron deposition in liver biopsies, are better predictors of response to IFN-alpha than the total Knodell score. Thirty-five unselected patients were studied who had hepatitis C treated with IFN-alpha between 1990 and 1993, and pretreatment serum iron indices and liver needle biopsies performed. Biopsies were divided for light microscopy and quantitative iron determination. H&E-stained slides were graded for components I, II, III, IV, and total Knodell score. Quantitative determinations were percentage of portal triads with inflammation, piecemeal necrosis, lymphoid aggregates, and inflamed bile ducts; percentage of lobules with inflammation or acidophilic bodies; and percentage of triads with positive iron stain. Complete responders (CR) to IFN-alpha were defined by normalization of serum alanine aminotransferase (< or = 40 IU/liter), and noncomplete responders (NCR) by partial or no response. Data were analyzed statistically. CR had < 40% of triads positive for iron (P = 0.02) and lower serum ferritin (P = 0.05) and higher scores for lobular necrosis (P = 0.04). The percentage of iron-positive triads correlated only with cirrhosis. Addition of cirrhosis to percentage of iron-positive triads did not improve the predictive power of the portal iron. CR and NCR did not differ with respect to total Knodell score or any of the other individual parameters except Knodell II.

Conclusions: (a) Individual features of lobular necrosis and iron staining in portal triads are better predictors of response to IFN-alpha than the total Knodell score.(ABSTRACT TRUNCATED AT 250 WORDS)