Clinical predictor score to identify patients at risk of poor viral load suppression at six months on antiretroviral therapy: results from a prospective cohort study in Johannesburg, South Africa

Abstract

Purpose: As countries work toward 90:90:90 targets, early identification of patients with inadequate response to antiretroviral therapy (ART) is critical for achieving optimal HIV treatment outcomes. We developed and evaluated a clinical prediction score (CPS) to identify HIV-positive patients at risk of poor viral load suppression at 6 months on ART. Patients and methods: We conducted a prospective cohort study of HIV-positive ART naïve adults (≥18 years) initiating standard first-line ART between February 2012 and April 2014 at Themba Lethu Clinic in Johannesburg, South Africa. We used Modified Poisson regression to estimate the association between patient characteristics and poor viral load suppression, defined as a viral load ≥400 copies/mL at 6 months on ART. We developed a CPS following the Spiegel Halter and Knill-Jones approach and determined the diagnostic accuracy compared to viral load as the "gold standard". We identified the optimal cutoff at which the CPS would identify those at risk of poor viral load suppression. Results: Among 353 patients, 67.7% had a viral load measurement at 6 months on ART and 30.1% of these were viremic (≥400 copies/mL). Male gender, platelet count <150 cells/mm³, ≥7 days late for ≥2 ARV visits, visual analog scale (VAS) <90% and <14.5 fL increase in mean cell volume from baseline to 6 months were included in the CPS. The optimal cutoff was 5 (≥5 vs <5; sensitivity [Se] 65.3%, specificity [Sp] 46.7%) and the CPS performed better than standard measures of adherence (eg, VAS Se 24.5%; Simplified Medication Adherence Questionnaire Se 26.5%). Conclusion: Our findings suggest a 6-month CPS may have the potential to identify patients at risk of poor viral load suppression. The CPS may be used to target patients who need intensive adherence support, with the caveat that there may be a three- to four-fold increase in the pool of patients identified for adherence counseling.

Keywords: algorithm; antiretroviral therapy; monitoring; resource limited; risk score; viral load.

Figure 1

Flowchart of the study participant in the LCM cohort study.

Figure 2

Diagnostic accuracy of the algorithm compared to viral load as “the gold standard”.