Health facility factors and quality of services to prevent mother-to-child HIV transmission in Côte d'Ivoire, Kenya, and Mozambique

Abstract

This study aimed to identify facility-level characteristics associated with prevention of mother-to-child HIV transmission service quality. This cross-sectional study sampled 60 health facilities in Mozambique, Côte d'Ivoire, and Kenya (20 per country). Performance score - the proportion of pregnant women tested for HIV in first antenatal care visit, multiplied by the proportion of HIV-positive pregnant women who received appropriate antiretroviral medications - was calculated for each facility using routine data from 2012 to 2013. Facility characteristics were ascertained during on-site visits, including workload. Associations between facility characteristics and performance were quantified using generalized linear models with robust standard errors, adjusting for country. Over six months, facilities saw 38,611 first antenatal care visits in total. On-site CD4 testing, Pima CD4 machine, air conditioning, and low or high (but not mid-level) patient volume were each associated with higher performance scores. Each additional first antenatal care visit per nurse per month was associated with a 4% (95% confidence interval: 1%-6%) decline in the odds that an HIV-positive pregnant woman would receive both HIV testing and antiretroviral medications. Physician workload was only modestly associated with performance. Investments in infrastructure and human resources - particularly nurses - may be critical to improve prevent mother-to-child HIV transmission service delivery and protect infants from HIV.

Keywords: Africa; HIV; highly active antiretroviral therapy; prevention; women.

Figure 1

Patient volume of health facilities and their associations with the likelihood of HIV-positive pregnant women being tested for HIV in first antenatal care visit and receiving appropriate antiretroviral medications, in 60 health facilities offering PMTCT services in Côte d’Ivoire, Kenya, and Mozambique. (a) Catchment area population, by quintile; (b) first antenatal care visits, by quintile; (c) deliveries, by quintile; and (d) postpartum visits, by quintile. The referent category is lowest quintile for all panels, as indicated by the red line at y = 1. p values are from Wald tests of the significance of the beta-coefficients of all categories jointly, with each category included in the regression model as an indicator variable. ANC: antenatal care; aOR: adjusted odds ratio; CI: confidence interval; PMTCT: prevention of mother-to-child transmission.