Tobacco Use Prevalence in Sub-Saharan Africa Modelled with Machine Learning

Strategic Insights -

Research from the University of Gondar in Ethiopia has analyzed data from 147,466 men to identify predictors of tobacco use in Sub-Saharan Africa. The study utilized machine learning algorithms to determine the key factors influencing tobacco use among men in the region between 2018 and 2023. The findings highlight the need for targeted public health interventions and the value of machine learning in identifying at-risk populations and addressing socio-cultural and economic factors influencing tobacco use.

Key Takeaways:

  • The study analyzed data from 147,466 men in Sub-Saharan Africa between 2018 and 2023 to identify predictors of tobacco use.
  • The researchers used various machine learning models, including Decision Tree, Logistic Regression, Random Forest, KNN, eXtreme Gradient Boosting (XGBoost), and AdaBoost, to identify the key predictors of tobacco use among men.
  • The study found that age, education, wealth index, religion, residence, internet use, occupation, age at first sex, number of sexual partners, and marital status were key predictors of tobacco use.
  • The XGBoost algorithm achieved an accuracy of 98% and an area under the curve (AUC) score of 97% in predicting tobacco use.
  • The study found a pooled tobacco use prevalence of 14.73% in Sub-Saharan Africa, with no significant variation between countries.
  • High tobacco use was observed in Mozambique, Zambia, Benin, Mali, Mauritania, Senegal, Guinea, Sierra Leone, and Liberia, with Tanzania, Benin, and Senegal reporting the highest rates.

Statistics:

  • Pooled tobacco use prevalence in Sub-Saharan Africa: 14.73%
  • Accuracy of XGBoost algorithm in predicting tobacco use: 98%
  • Area under the curve (AUC) score of XGBoost algorithm: 97%

Sources:

  • Exploring explainable machine learning algorithms to model predictors of tobacco use among men in Sub Sahara Africa between 2018 and 2023. Scientific Reports, 2025;15(1):24646.
  • Nature Portfolio. Heidelberger Platz 3, Berlin, 14197, Germany. (Nature Publishing Group - www.nature.com/; Scientific Reports - www.nature.com/srep/)
  • University of Gondar, Dept. of Health Informatics, Institute of Public Health, Gondar, Ethiopia
  • NewsRx. University of Gondar Reports Findings in Machine Learning (Exploring explainable machine learning algorithms to model predictors of tobacco use among men in Sub Sahara Africa between 2018 and 2023). Journal of Engineering. July 21, 2025; p 3684.