Socio-Behavioral and Spatial Determinants of HIV/AIDS Incidence in Ghana: An Ecological Cross-Sectional Study with Explainable Machine Learning

Read the full article See related articles

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

Background: Despite the national decline in cases, Ghana continues to experience significant regional disparities in HIV/AIDS incidence due to inequities in social factors, including education, stigma, HIV awareness, and access to ART. Such inequalities are often hidden in national statistics, which reduce the accuracy of public health measures. Methods: A unified regional dataset was created using GHS, GAC, MoH, GSS, UNAIDS, and World Bank data from 2000 to 2022, which combined sociobehavioral and health infrastructure factors. Using spatial clustering and choropleth mapping, high-incidence areas were identified and regional vulnerability was assessed. Random Forest and XGBoost analyzed key structural features via SHAP values, PDPs, and counterfactual simulations. Results: Spatial clustering and choropleth mapping revealed a spike in HIV incidence in the Greater Accra, Ashanti, and Central regions. This pattern was linked to factors such as high urbanization, social stigma, and unequal access to ART. Clustering identified three main regional typologies based on the health indicators. SHAP and PDP analyses indicated that HIV incidence declined abruptly when educational access exceeded 60%, or ART coverage surpassed 45%. Residual mapping suggested possible under-reporting of HIV incidence or latent socio-structural buffers in rural areas. A 10% increase in education or awareness reduced the incidence by up to 16% in the high-burden regions. Conclusions: In Ghana, HIV/AIDS incidence is influenced by access to healthcare and various spatial and social disparities. This study revealed the importance of creating policies that support education, reduce stigma, and ensure equal access to ART across different regions. Through explainable machine learning, the influence of behavioral and geographic factors on Ghana’s HIV incidence was examined.

Article activity feed