Scholarlink

Background <p>Vector-borne and vaccine-preventable diseases such as malaria, dengue, chikungunya, and measles remain major public health challenges and a leading cause of morbidity and mortality in Africa, accounting for a significant proportion of the region’s disease burden. Factors including fragile health systems, rapid urbanization, and climate variability create an environment conducive to disease outbreaks and hinder socio-economic development. Despite the interconnected nature of these diseases, cross-disease vulnerability modeling using integrated environmental and social determinants remains limited in the African context.</p> Methods <p>This study proposes a predictive framework to identify African countries at heightened risk for multiple disease outbreaks, using malaria as a baseline for assessing susceptibility to dengue, chikungunya, and measles. Data from 40 African countries were compiled across 10 indicators reflecting climatic, demographic, and health system conditions. The methodology combined descriptive statistics, Random Forest classification, Lasso regression, Hotspot Analysis, Principal Component Analysis (PCA), and the development of a novel Cross-Disease Vulnerability Index (CDVI).</p> Results <p>Our findings revealed distinct clusters of high vulnerability across Central, Southern, and Western Africa. The Random Forest model achieved a classification accuracy of 87.5%, while the fine-tuned Lasso regression demonstrated a strong predictive performance with an R² of 0.8467. Rainfall, urbanization, population density, and proportion of children under age 15 emerged as the most influential predictors of disease vulnerability. The CDVI showed a strong positive association with malaria case burdens (ρ = +0.72, <i>p</i> &lt; 0.0028), validating its potential as a proxy for cross-disease susceptibility.</p> Conclusion <p>The value of integrated modeling approaches, including the CDVI, can guide targeted public health interventions and improve epidemic preparedness across Africa.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Modeling cross disease vulnerability in Africa using environmental and social determinants to predict malaria risk and susceptibility to dengue chikungunya and measles

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月24日

查看全文
  • Bernard Sefah,
  • Eric Abakah,
  • Davidson Bosangi,
  • Derrick Asante,
  • Francis Boateng,
  • Theresa Serwaa Agyemang,
  • Collins Affum

摘要

Background

Vector-borne and vaccine-preventable diseases such as malaria, dengue, chikungunya, and measles remain major public health challenges and a leading cause of morbidity and mortality in Africa, accounting for a significant proportion of the region’s disease burden. Factors including fragile health systems, rapid urbanization, and climate variability create an environment conducive to disease outbreaks and hinder socio-economic development. Despite the interconnected nature of these diseases, cross-disease vulnerability modeling using integrated environmental and social determinants remains limited in the African context.

Methods

This study proposes a predictive framework to identify African countries at heightened risk for multiple disease outbreaks, using malaria as a baseline for assessing susceptibility to dengue, chikungunya, and measles. Data from 40 African countries were compiled across 10 indicators reflecting climatic, demographic, and health system conditions. The methodology combined descriptive statistics, Random Forest classification, Lasso regression, Hotspot Analysis, Principal Component Analysis (PCA), and the development of a novel Cross-Disease Vulnerability Index (CDVI).

Results

Our findings revealed distinct clusters of high vulnerability across Central, Southern, and Western Africa. The Random Forest model achieved a classification accuracy of 87.5%, while the fine-tuned Lasso regression demonstrated a strong predictive performance with an R² of 0.8467. Rainfall, urbanization, population density, and proportion of children under age 15 emerged as the most influential predictors of disease vulnerability. The CDVI showed a strong positive association with malaria case burdens (ρ = +0.72, p < 0.0028), validating its potential as a proxy for cross-disease susceptibility.

Conclusion

The value of integrated modeling approaches, including the CDVI, can guide targeted public health interventions and improve epidemic preparedness across Africa.