Not all missed doses are the same: sustained NNRTI treatment interruptions predict HIV rebound at low-to-moderate adherence levels

Abstract

Background: While the relationship between average adherence to HIV potent antiretroviral therapy is well defined, the relationship between patterns of adherence within adherence strata has not been investigated. We examined medication event monitoring system (MEMS) defined adherence patterns and their relation to subsequent virologic rebound.

Methods and results: We selected subjects with at least 3-months of previous virologic suppression on a non-nucleoside reverse transcriptase inhibitor (NNRTI)-based regimen from two prospective cohorts in France and North America. We assessed the risk of virologic rebound, defined as HIV RNA of >400 copies/mL according to several MEMS adherence measurements. Seventy two subjects were studied, five of them experienced virologic rebound. Subjects with and without virologic rebound had similar baseline characteristics including treatment durations, regimen (efavirenz vs nevirapine), and dosing schedule. Each 10% increase in average adherence decreased the risk of virologic rebound (OR = 0.56; 95% confidence interval (CI) [0.37, 0.81], P<0.002). Each additional consecutive day off therapy for the longest treatment interruption (OR = 1.34; 95%CI [1.15, 1.68], P<0.0001) and each additional treatment interruption for more than 2 days (OR = 1.38; 95%CI [1.13, 1.77], P<0.002) increased the risk of virologic rebound. In those with low-to-moderate adherence (i.e. <80%), treatment interruption duration (16.2 days versus 6.1 days in the control group, P<0.02), but not average adherence (53.1% vs 55.9%, respectively, P = 0.65) was significantly associated with virologic rebound.

Conclusions: Sustained treatment interruption may pose a greater risk of virologic rebound on NNRTI therapy than the same number of interspersed missed doses at low-to-moderate adherence.

Figure 1. Predicted and observed risk of viral control according to the longer interval of treatment discontinuation, POSOVIR and REACH cohorts.

Figure 2. Relationship between average adherence and longer treatment interruption among subjects with (red) and without (green and blue) virologic rebound, POSOVIR and REACH cohorts.

- The red lines on the X and Y-axis correspond to mean average adherence (%) and treatment interruption duration (days), respectively, among subjects with subsequent HIV RNA≥400 copies/ml. The blue lines on the X and Y-axis correspond to mean average adherence (%) and treatment interruption duration (days), respectively, among subjects with subsequent HIV RNA<400 copies/ml and low-to-moderate adherence (<80%). The difference in treatment interruption duration, but not adherence rate, is statistically significant between those with HIV RNA≥400 copies/ml and those with HIV RNA<400 copies/ml.