Public health surveillance systems in Kenya are crucial for monitoring diseases and managing public health interventions effectively. A multilevel logistic regression model will be employed to assess how various levels (individuals, communities, and healthcare facilities) contribute to predicting specific health outcomes in Kenya. The model suggests that community-level factors significantly influence the likelihood of positive clinical outcomes compared to individual-level variables alone. Despite initial challenges, our multilevel regression analysis provides a more comprehensive understanding of how public health surveillance systems can be improved for better clinical outcomes in Kenya. Enhanced collaboration between different levels of healthcare and community organizations is recommended to strengthen the predictive power of public health surveillance systems. Public Health Surveillance, Multilevel Regression Analysis, Clinical Outcomes, Kenya Treatment effect was estimated with logit (pᵢ) =₀+^ Xᵢ, and uncertainty reported using confidence-interval based inference.
Odinga et al. (Thu,) studied this question.