Monitoring Virologic Responses to Antiretroviral Therapy in HIV-Infected Adults in Kenya: Evaluation of a Low-Cost Viral Load Assay

Background: A key advantage of monitoring HIV viral load (VL) in persons receiving antiretroviral therapy (ART) is the ability to detect virologic failure before clinical deterioration or resistance occurs. Detection of virologic failure will help clarify the need for enhanced adherence counseling or a change to second-line therapy. Low-cost, locally performable alternates to expensive VL assays are needed where resources are limited. Methodology/Principal Findings: We monitored the response to 48-week ART in 100 treatment-naive Kenyan adults using a low-cost VL measurement, the Cavidi reverse transcriptase (RT) assay and gold-standard assays, Roche RNA PCR and Bayer Versant HIV-1 RNA (bDNA) assays. In Altman-Bland plots, the mean difference in viral loads between the three assays was small (< 0.5 log(10) copies/mL). However, the limits of agreement between the methods exceeded the biologically relevant change of 0.5 log copies/ml. Therefore, the RT assay cannot be used interchangeably with the other assays to monitor individual patients. The RT assay was 100% sensitive in detecting viral loads of >= 400 copies/ml compared to gold-standard assays. After 24 weeks of treatment, viral load measured by the RT assay was undetectable in 95% of 65 patients with undetectable RNA PCR VL (< 400 copies/ml), 90% of 67 patients with undetectable bDNA VL, and 96% of 57 patients with undetectable VL in both RNA PCR and bDNA assays. The negative predictive value of the RT assay was 100% compared to either assay; the positive predictive value was 86% compared to RNA PCR and 70% compared to bDNA. Conclusion: The RT assay compared well with gold standard assays. Our study highlights the importance of not interchanging viral load assays when monitoring an individual patient. Furthermore, the RT assay may be limited by low positive predictive values when used in populations with low prevalence of virologic failure.