Discordant increases in CD4 cell count relative to plasma viral load in a closely followed cohort of patients initiating antiretroviral therapy

Background: In HIV-positive persons receiving antiretroviral therapy, CD4 cell responses are associated with optimal suppression of viral replication. However, increases in CD4 cell counts in the absence of viral suppression have been reported. We characterized plasma viral load (pVL) and CD4 cell count increases in closely followed patients to evaluate determinants and the prevalence of CD4 cell responses at a populational level. Methods: All HIV-positive patients in the province of British Columbia, Canada, who were antiretroviral naive and initiated therapy between August 1996 and May 1998 were eligible for the study. The selection criteria were that patients had to have CD4 cell counts and pVLs measured at baseline and at least once during eight 16-week periods after the initiation of therapy. We characterized CD4 cell responses and sought patients who had a "discordant" increase at 1 year, which was defined as an increase in CD4 cell count of greater than or equal to50/mm(3) with a <1 log(10) decrease in pVL. We also evaluated adherence and antiretroviral use. Results: Overall, when baseline and 1-year pVLs and CD4 cell Counts were compared, 6.2% of patients had CD4 cell count increases without pVL decreases of ! I log(10). However, when all pVLs before I year were considered, 92% of the discordant increases could be attributed to prior transient or partial viral Suppression. Furthermore, although substantial increases in CD4 cell counts were observed in transient virologic responders, the cumulative number of antiretroviral agents used by this group was significantly higher than that used by full virologic responders (p < .001). Conclusions: Our results demonstrate that virtually all CD4 cell count increases can be attributed to transient or partial pVL suppression. Unmeasured pVL suppression likely explains discordant responses that have been previously reported. Similarities between transient and full virologic responders also appear to be time limited and are often associated with greater cumulative use of antiretroviral therapy by transient virologic responders.