Predicting Early Viral Control under Direct-Acting Antiviral Therapy for Chronic Hepatitis C Virus Using Pretreatment Immunological Markers

Abstract

Recent introduction of all-oral direct-acting antiviral (DAA) treatment has revolutionized care of patients with chronic hepatitis C virus (HCV) infection. Regrettably, the high cost of DAA treatment is burdensome for healthcare systems and may be prohibitive for some patients who would otherwise benefit. Understanding how patient-related factors influence individual responses to DAA treatment may lead to more efficient prescribing. In this observational study, patients with chronic HCV infection were comprehensively monitored by flow cytometry to identify pretreatment immunological variables that predicted HCV RNA negativity within 4 weeks of commencing DAA treatment. Twenty-three patients [genotype 1a (n = 10), 1b (n = 9), and 3 (n = 4)] were treated with daclatasvir plus sofosbuvir (SOF) (n = 15), ledipasvir plus SOF (n = 4), or ritonavir-boosted paritaprevir, ombitasvir, and dasabuvir (n = 4). DAA treatment most prominently altered the distribution of CD8⁺ memory T cell subsets. Knowing only pretreatment frequencies of CD3⁺ and naive CD8⁺ T cells allowed correct classification of 83% of patients as "fast" (HCV RNA-negative by 4 weeks) or "slow" responders. In a prospective cohort, these parameters correctly classified 90% of patients. Slow responders exhibited higher frequencies of CD3⁺ T cells, CD8⁺ T_EM cells, and CD5^high CD27^- CD57⁺ CD8⁺ chronically activated T cells, which is attributed to bystander hyperactivation of virus-non-specific CD8⁺ T cells. Taken together, non-specific, systemic CD8⁺ T cell activation predicted a longer time to viral clearance. This discovery allows pretreatment identification of individuals who may not require a full 12-week course of DAA therapy; in turn, this could lead to individualized prescribing and more efficient resource allocation.

Trial registration: ClinicalTrials.gov NCT02904603.

Keywords: biomarker; classifier; direct-acting antiviral therapy; hepatitis C virus; immune monitoring; memory T cell; non-classical monocyte.

Figure 1

Statistical analyses of flow cytometry dataset. (A) The first two principal components (PC1, PC2) of entire dataset of baseline standardized leukocyte frequencies partly distinguished fast (red) and slow (blue) responders. (B) After filtering the baseline dataset for leukocyte populations whose frequencies were significantly influenced by direct-acting antiviral treatments, the first two principal components of standardized leukocyte frequencies separated fast (red) and slow (blue) responders. (C) Comparison of baseline CD3⁺ T cell frequency between fast and slow responders. (D) Comparison of baseline naïve CD8⁺ T cell frequency between fast and slow responders. (E) Comparison of baseline CD8⁺ T_EM cell frequency between fast and slow responders. (F) Baseline CD3⁺ T cell frequency and baseline naïve CD8⁺ T cell frequency were entered as independent variables in a binary logistic regression model. A cutoff probability of 0.66 for scoring fast and slow responders was determined using receiver operator characteristic curve analysis, which gave a test sensitivity of 75.0% and specificity of 91.0%.

Figure 2

Generalized activation of peripheral blood CD8⁺ T cells in slow responders. (A) Frequencies of CD27⁻ CD8⁺ T cells in fast and slow responders. (B) Frequencies of CD57⁺ CD8⁺ T cells in fast and slow responders. (C) Frequencies of chronically activated CD27⁻ CD57⁺ CD8⁺ T cells in fast and slow responders. (D) Visual representation of the method used to estimate the dispersion of CD5 expression in CD8⁺ T cells. The examples represent one fast and one slow responder from samples of n = 7 and n = 8, respectively. The first pair of histograms show CD5 fluorescence intensities of >1 plotted on a log-axis. The second pair of histograms show log₁₀-transformed values plotted on a linear-axis and their respective medians (Med.). The third pair of histograms show absolute deviation of log₁₀-transformed values from median (ADM) and the respective medians (MADM). (E) CD5 expression by CD8⁺ T cells from fast and slow responders estimated by median fluorescence intensity. (F) MADM_Log(CD5) in CD8⁺ T cells from fast and slow responders. Assessing the spread of CD5 expression in CD8⁺ T cells discriminates better between fast and slow responders. (G) Downregulation of CD5 expression appears to be confined to CD27⁻ CD8⁺ T cells.

Figure 3

A consolidated flow cytometry panel and recommended gating strategy. Example data from one patient with chronic hepatitis C virus infection is shown.