What question did this study set out to answer?

This study aims to develop a Bayesian hierarchical model to evaluate the adoption rates of disease surveillance systems across Nigeria and project future trends.

March 13, 2026Open Access

A Bayesian Hierarchical Model for Evaluating the Adoption of Public Health Surveillance Systems in Nigeria, 2000–2026

Key Points

This study aims to develop a Bayesian hierarchical model to evaluate the adoption rates of disease surveillance systems across Nigeria and project future trends.
Developed a Bayesian hierarchical logistic model using state-level panel data on surveillance system implementation.
Specified the model to capture adoption probability, covariates, temporal trends, and state-level random effects.
Estimated parameters using Hamiltonian Monte Carlo.
Projected a median national adoption rate of 67% by the end of the period, with a 95% credible interval of 61–73%.
Found substantial inter-state variation in adoption rates, particularly between northern and southern states.
Estimated a posterior probability exceeding 0.85 that northern states have lower adoption rates than southern states.

Abstract

"background": "Public health surveillance systems are critical for disease control, yet their adoption across diverse administrative regions in Nigeria remains uneven and poorly quantified. Existing evaluations often lack a formal statistical framework to integrate multi-level data and account for spatial and temporal heterogeneity. ", "purpose and objectives": "This study aimed to develop and apply a novel Bayesian hierarchical model to evaluate the adoption rates of integrated disease surveillance and response (IDSR) systems across Nigerian states, and to project future trajectories under current policy conditions. ", "methodology": "We constructed a Bayesian hierarchical logistic model using state-level panel data on surveillance system implementation. The core model is specified as (p{it) = \ + \ Xit + \ + \ +, where pit is the probability of full adoption in state i at time t, Xit are covariates, \ captures temporal trends, and \ᵢ are state-level random effects. Parameters were estimated using Hamiltonian Monte Carlo. ", "findings": "Model projections indicate a median national adoption rate of 67% (95% credible interval: 61–73%) by the end of the projection period, with substantial inter-state variation. The posterior probability that the adoption rate in northern states lags behind southern states exceeded 0. 85. ", "conclusion": "The methodological approach provides a robust, probabilistic framework for evaluating public health system adoption. Findings reveal that, without intervention, significant geographical inequities in surveillance capacity will persist. ", "recommendations": "Policy should prioritise targeted, data-driven support for low-adoption regions. Future evaluations of health systems should employ similar hierarchical models to formally incorporate uncertainty and heterogeneity. ", "key words": "Bayesian statistics, hierarchical model, public health surveillance, health systems, adoption, Nigeria", "contribution statement": "This paper introduces a novel Bayesian hierarchical modelling framework for the spatio-temporal analysis of health system adoption

Read Full Paperexternally

Demander à l'IA

Bookmark

View Full Paper