Treatment outcomes and cost-effectiveness of shifting management of stable ART patients to nurses in South Africa: an observational cohort

Abstract

Background: To address human resource and infrastructure shortages, resource-constrained countries are being encouraged to shift HIV care to lesser trained care providers and lower level health care facilities. This study evaluated the cost-effectiveness of down-referring stable antiretroviral therapy (ART) patients from a doctor-managed, hospital-based ART clinic to a nurse-managed primary health care facility in Johannesburg, South Africa.

Methods and findings: Criteria for down-referral were stable ART (≥11 mo), undetectable viral load within the previous 10 mo, CD4>200 cells/mm(3), <5% weight loss over the last three visits, and no opportunistic infections. All patients down-referred from the treatment-initiation site to the down-referral site between 1 February 2008 and 1 January 2009 were compared to a matched sample of patients eligible for down-referral but not down-referred. Outcomes were assigned based on vital and health status 12 mo after down-referral eligibility and the average cost per outcome estimated from patient medical record data. The down-referral site (n = 712) experienced less death and loss to follow up than the treatment-initiation site (n = 2,136) (1.7% versus 6.2%, relative risk = 0.27, 95% CI 0.15-0.49). The average cost per patient-year for those in care and responding at 12 mo was US$492 for down-referred patients and US$551 for patients remaining at the treatment-initiation site (p<0.0001), a savings of 11%. Down-referral was the cost-effective strategy for eligible patients.

Conclusions: Twelve-month outcomes of stable ART patients who are down-referred to a primary health clinic are as good as, or better than, the outcomes of similar patients who are maintained at a hospital-based ART clinic. The cost of treatment with down-referral is lower across all outcomes and would save 11% for patients who remain in care and respond to treatment. These results suggest that this strategy would increase treatment capacity and conserve resources without compromising patient outcomes.

Figure 1. Decision process for assigning HIV treatment outcomes.

Patients were placed in a mutually exclusive patient outcome category 12 mo after study enrolment – no longer in care, in care and responding or in care and not responding. Patient outcomes were defined based on the patient's vital status, presence in the clinic, viral load or CD4 count at 12 mo after study enrolment. For those patients alive and in treatment, viral load was the preferred outcome indicator, but in the absence of viral load CD4 count was used and if neither were available then it was assumed the patient was in care and responding based on their presence in the clinic. The diagnostic result closest to 12 mo, but within 3 mo (9–15 mo) was used.

Figure 2. Selection of study participants.

All patients initiated on ART at the treatment-initiation site were considered for this study. The patient population was divided into those down-referred and those not down-referred (maintained at the treatment-initiation site). Patients were excluded if they (1) had missing matching variables, (2) were on non-standard ARV regimens, (3) had insufficient potential follow-up time, (4) were eligible/down-referred outside the study period, (5) initiated ART prior to the national rollout, (6) were down-referred to another site (i.e., not the study site), or (7) were <18 y old. Those down-referred patients included in the study were matched 1∶3 with patients maintained at the treatment-initiation site. DR, down-referral; TI, treatment-initiation site.