Antihypertensive Pharmacotherapy Gaps in Nigeria: A Predictive Machine Learning Analysis of Treatment Uptake Amid Macroeconomic Shock, Using NDHS 2023–24
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background
Hypertension is the most important modifiable cardiovascular risk factor worldwide, and the prevalence is increasing in sub-Saharan Africa. Nigeria’s newly released 2023–24 Demographic and Health Survey (NDHS) provides the first opportunity to explore national-level non-uptake of antihypertensive treatment using a machine-learning cascade framework, although survey fieldwork was conducted amid the unprecedented shock of fuel subsidy removal and currency devaluation in Nigeria.
Objectives
To identify correlates of antihypertensive treatment non-uptake (Gap 2) among the diagnosed adults in Nigeria; test if the non-uptake varied based on when the survey was conducted during this macroeconomic shock; and compare four predictive algorithms.
Methods
We used the 2023–24 Nigeria Demographic and Health Survey (NDHS) data (2,975 women diagnosed with hypertension and 529 men diagnosed with hypertension aged 15-49) to fit survey-weighted logistic regression models separately by sex and evaluated sex-by-predictor interactions in a single pooled model. We then compared the survey-weighted logistic regression model with the elastic net, random forest, and gradient boosting (XGBoost) models, all properly weighted, using held-out test-set AUC.
Results
The timing of fieldwork interviews was a significant risk factor for women (OR=1.14 per month; 95% CI: 1.06–1.22; p<0.001) but not for men, and this sex difference was confirmed in the formal interaction test (p=0.016). This study tested the interaction of sex with each geopolitical zone, with the strongest result being a sex-reversed pattern in zones protective for women, showing these zones were significant risk factors for men (ORs 2.28–5.77); interaction testing (all p≤0.007) confirmed this. No interaction was observed between diabetes and sex (p=0.170); instead, diabetes was protective for women (OR=0.34, p<0.001). For pooled samples, wealth was associated with non-uptake (OR=0.59; p=0.012), and this appeared significant only for women (OR=0.62; p=0.026), in keeping with the richest-vs-poorest estimate in Table 2. All three ML algorithms had similar AUC for women (0.61–0.63) and lower, near-chance performance for men (0.56–0.59), reflecting the much smaller number of diagnosed men.
Conclusions
There is a large disparity in the rate of treatment and management of HTN across sexes, geopolitical zones, and macro-economic environments, making a single uniform national intervention model impractical. In contrast, an earlier study in Africa reported that similar algorithmic complexity was useful in predicting cardiovascular risk; this did not happen in the current study. The proposed programs are to build programs by sex and zone, integrate hypertension screenings into chronic disease and/or maternal health trigger points, and better understand the resilience of the pharmacy supply chain.
