Naomi: a new modelling tool for estimating HIV epidemic indicators at the district level in sub-Saharan Africa

Abstract

Introduction: HIV planning requires granular estimates for the number of people living with HIV (PLHIV), antiretroviral treatment (ART) coverage and unmet need, and new HIV infections by district, or equivalent subnational administrative level. We developed a Bayesian small-area estimation model, called Naomi, to estimate these quantities stratified by subnational administrative units, sex, and five-year age groups.

Methods: Small-area regressions for HIV prevalence, ART coverage and HIV incidence were jointly calibrated using subnational household survey data on all three indicators, routine antenatal service delivery data on HIV prevalence and ART coverage among pregnant women, and service delivery data on the number of PLHIV receiving ART. Incidence was modelled by district-level HIV prevalence and ART coverage. Model outputs of counts and rates for each indicator were aggregated to multiple geographic and demographic stratifications of interest. The model was estimated in an empirical Bayes framework, furnishing probabilistic uncertainty ranges for all output indicators. Example results were presented using data from Malawi during 2016-2018.

Results: Adult HIV prevalence in September 2018 ranged from 3.2% to 17.1% across Malawi's districts and was higher in southern districts and in metropolitan areas. ART coverage was more homogenous, ranging from 75% to 82%. The largest number of PLHIV was among ages 35 to 39 for both women and men, while the most untreated PLHIV were among ages 25 to 29 for women and 30 to 34 for men. Relative uncertainty was larger for the untreated PLHIV than the number on ART or total PLHIV. Among clients receiving ART at facilities in Lilongwe city, an estimated 71% (95% CI, 61% to 79%) resided in Lilongwe city, 20% (14% to 27%) in Lilongwe district outside the metropolis, and 9% (6% to 12%) in neighbouring Dowa district. Thirty-eight percent (26% to 50%) of Lilongwe rural residents and 39% (27% to 50%) of Dowa residents received treatment at facilities in Lilongwe city.

Conclusions: The Naomi model synthesizes multiple subnational data sources to furnish estimates of key indicators for HIV programme planning, resource allocation, and target setting. Further model development to meet evolving HIV policy priorities and programme need should be accompanied by continued strengthening and understanding of routine health system data.

Keywords: Bayesian statistics; HIV estimates; joint modelling; routine data; small-area estimation.

Figure 1

Overview of model components and processes. ANC, antenatal clinic; ART, antiretroviral treatment; PLHIV, people living with HIV.

Figure 2

Examples of model estimates. (a) HIV prevalence among adults age 15 to 49 years at all levels of the area hierarchy in September 2018. (b) Antiretroviral treatment (ART) coverage among adults age 15 years and older by district and four metropolitan areas in March 2016 and September 2018. (c) HIV incidence rate among adults 15 to 49 years (colour) and annual number of new HIV infections among adults 15 years and older (size of bubble) in September 2018. Estimates reflect posterior mean. Example results did not include the most current Malawi HIV programme data, and some household survey clusters were randomly allocated to districts; refer to UNAIDS AIDSinfo for official Malawi HIV estimates [32].

Figure 3

Sex and five‐year age group stratified results at national level in September 2018. Similar results are produced by region and by district. Line ranges reflect 95% credible interval ranges. Population is a fixed model input and does not has uncertainty ranges (top left). For new infections plot (top right), note that the model does not produce estimates of mother‐to‐child HIV infections, but the number of children living with HIV (top centre) are modelled based on relative levels of child to adult prevalence and paediatric antiretroviral treatment (ART) numbers. Example results did not include the most current Malawi HIV programme data, and some household survey clusters were randomly allocated to districts; refer to UNAIDS AIDSinfo for official Malawi HIV estimates [32]. PLHIV, people living with HIV.

Figure 4

Comparison of district‐level data and model estimates for HIV prevalence and antiretroviral treatment (ART) coverage in March 2016. (a) HIV prevalence among adults 15 to 49 years; (b) HIV prevalence among antenatal clinic (ANC) clients; (c) ART coverage among adults 15 to 64 years; and (d) ART coverage prior to the first ANC visit. Thick black dash and vertical ranges show model estimates and 95% credible intervals. Narrow vertical light blue lines indicate 80% posterior predictive intervals, representing the range in which 80% probability new observations would fall. Posterior predictive ranges account for both uncertainty about true prevalence and ART coverage and sampling variability based on the sample size for each observation. For HIV prevalence results (panels a and b), districts are sequenced in decreasing order according to estimated HIV prevalence among ages 15 to 49 in March 2016. For ART coverage (panels c and d), results are sequenced in decreasing order according to estimated ART coverage ages 15 to 64 in March 2016. Red points indicate data observations from household surveys (a and c) or routine antenatal HIV testing (b and d). In (a) data points represent district HIV prevalence estimates from two surveys, with each has a different 80% posterior predictive intervals reflecting the sample size and age distribution for that survey. In ANC data plots (b and d), for comparison the light grey dots indicate posterior mean estimates for prevalence ages 15 to 49 and ART coverage ages 15 to 64 shown in panels (a) and (c), respectively. *District data for Malawi population HIV impact assessment (MPHIA) 2015 to 2016 survey are based on random allocation of survey clusters to districts within each of seven survey strata. MDHS, Malawi demographic and health survey.

Figure 5

Results of antiretroviral treatment (ART) attendance model in September 2018 for three districts in central Malawi: Lilongwe city, Lilongwe district excluding the metropolitan area (rural), and Dowa district bordering Lilongwe to the north. (a) Estimated number of adult (age 15 years and older) residents on ART compared to number of adults receiving ART at health facilities in each district. (b) Percentage who receives ART at health facilities in each district by district of residence. (c) Distribution of district of residence for ART clients attending facilities in each district. For (b) and (c), bars are presented for all neighbouring districts. Bar heights indicate posterior mean and vertical ranges indicate 95% credible intervals. Example results did not include the most current Malawi HIV programme data, and some household survey clusters were randomly allocated to districts; refer to UNAIDS AIDSinfo for official Malawi HIV estimates [32].