Proficiency of transient elastography compared to liver biopsy for the assessment of fibrosis in HIV/HBV-coinfected patients

Abstract

Transient elastography (TE) is a noninvasive technique to evaluate liver fibrosis. We compared the performance of TE with liver biopsy (LB) in patients with human immunodeficiency virus (HIV) and hepatitis B virus (HBV) coinfection. Patients prospectively underwent TE and LB. The diagnosis accuracy of TE was calculated using receiver operating characteristic (ROC) curves for different stages of fibrosis, and optimal cut-off values were defined. A sequential algorithm combining TE with biochemical score (Fibrotest) is proposed. Fifty-seven patients had both TE and LB (median time: 3 days) and two with proven cirrhosis, only TE. Forty-six (78%) were under antiretroviral therapy with anti-HBV drugs in 98%, and 19 (32%) had elevated alanine aminotransferase (ALT). A significant correlation was observed between liver stiffness measurement (LSM) and METAVIR fibrosis stages (P < 0.0001). Patients with elevated ALT tended to have higher LSM than those with normal ALT. The areas under the ROC curves were 0.85 for significant fibrosis (≥ F2), 0.92 for advanced fibrosis (≥ F3) and 0.96 for cirrhosis. Using a cut-off of 5.9 kPa for F ≥ 2 and 7.6 kPa for F ≥ 3, the diagnosis accuracy was 83% and 86%, respectively. With an algorithm combining TE and Fibrotest, 97% of patients were well classified for significant fibrosis. Using this algorithm, the need for LB can be reduced by 67%. In HIV/HBV-coinfected patients, most of them with normal ALT under antiretroviral treatment including HBV active drugs, TE was proficient in discriminating moderate to severe fibrosis from minimal liver disease.