Introduction: meningitis disease remains a major public health problem in the African meningitis belt. The objective of the study was to describe the epidemiological situation of meningitis disease and control measures implemented from 2010 to 2024 in Africa. Methods: a cross-sectional study was conducted from 2010 to 2024. Number of cases, deaths, case fatality rates, epidemics, pathogens, immunization coverage were collected from datasets of the World Health Organization and countries. Results: from 2010 to 2024 the number of suspected meningitis cases decreased from 30,103 to 26,298 and case fatality rate decreased from 10.8% to 5.2%. From 2011 to 2024, twelve (12) countries of the African meningitis belt experienced bacterial meningitis epidemics and Nigeria and Niger the most affected. The predominant pathogens found were N. meningitidis serogroups C, W and S. pneumoniae. From 2010 to 2024, MenACV have been rolled out in 23 of the 26 countries in the African meningitis belt. Over 400 million persons aged 9 months to 29 years old have been vaccinated with MenACV. To implement the framework to defeat meningitis by 2030 that envisions Africa free of meningitis, landscape risk analysis conducted in 2021 resulted in 13 countries at high risk, 25 at medium risk and nine at low risk. Conclusion: the MenACV rollout led to the dramatic reduction of meningitis cases and deaths, and elimination of meningitis caused by N. meningitidis A. However, to eliminate bacterial meningitis epidemics countries should implement and monitor plans to defeat meningitis by 2030.
Intentional manipulation of invoices that lead to undervaluation of trade goods is the most common type of customs fraud to avoid ad valorem duties and taxes. To secure government revenue without interrupting legitimate trade flows, customs administrations around the world strive to develop ways to detect illicit trades. This paper proposes DATE, a model of Dual-task Attentive Tree-aware Embedding, to classify and rank illegal trade flows that contribute the most to the overall customs revenue when caught. The strength of DATE comes from combining a tree-based model for interpretability and transaction-level embeddings with dual attention mechanisms. To accurately identify illicit transactions and predict tax revenue, DATE learns simultaneously from illicitness and surtax of each transaction. With a five-year amount of customs import data with a test illicit ratio of 2.24%, DATE shows a remarkable precision of 92.7% on illegal cases and a recall of 49.3% on revenue after inspecting only 1% of all trade flows. We also discuss issues on deploying DATE in Nigeria Customs Service, in collaboration with the World Customs Organization.
