# Using Biological Variables and Social Determinants to Predict Malaria and Anemia among Children in Senegal

**Authors:** Boubacar Sow, Hiroki Suguri, Hamid Mukhtar, Hafiz Farooq Ahmad  
**arXiv:** [2108.03601](https://arxiv.org/abs/2108.03601)  
**Date:** 2021-08-08  
**Summary page:** https://www.summarizepaper.com/en/paper/2108.03601v1/

## Key points

- Integrating machine learning techniques in healthcare has become increasingly common
- Machine learning offers significant contributions to improving clinical care and health decision planning
- Anemia and malaria are two life-threatening diseases that specifically affect the red blood cells and reduce hemoglobin production
- The research paper focuses on analyzing child health data in Senegal using four machine learning algorithms (KNN, Random Forests, SVM, and Naïve Bayes) implemented in Python
- The main objective of the study is to investigate large-scale data from The Demographic and Health Survey (DHS) in order to uncover hidden information related to anemia and malaria
- Two classification models for these blood disorders are presented using biological variables and social determinants
- The findings have the potential to significantly improve child healthcare in Senegal by eradicating anemia and malaria while reducing the child mortality rate
- The authors come from various academic backgrounds including Japan, Pakistan, and Saudi Arabia, contributing to a multidisciplinary approach towards addressing anemia and malaria among children in Senegal
- Leveraging machine learning algorithms along with comprehensive data analysis can improve healthcare outcomes for children suffering from anemia and malaria.

## Summary

Integrating machine learning techniques in healthcare has become increasingly common, offering significant contributions to improving clinical care and health decision planning. In Africa, anemia and malaria are two life-threatening diseases that specifically affect the red blood cells and reduce hemoglobin production. This research paper focuses on analyzing child health data in Senegal using four machine learning algorithms (KNN, Random Forests, SVM, and Naïve Bayes) implemented in Python. The main objective of this study is to investigate large-scale data from The Demographic and Health Survey (DHS) in order to uncover hidden information related to anemia and malaria. By utilizing biological variables and social determinants, the researchers present two classification models for these blood disorders. The findings of this research have the potential to significantly improve child healthcare in Senegal by eradicating anemia and malaria while also reducing the child mortality rate. By leveraging machine learning techniques and analyzing comprehensive data sets, this study aims to provide valuable insights that can inform effective strategies for combating these diseases. Additionally, the authors of this paper come from various academic backgrounds including Graduate School of Project Design at Miyagi University in Japan, School of Electrical Engineering and Computer Science at National University of Sciences and Technology (NUST) in Pakistan, as well as the Department of Computer Science at King Faisal University in Saudi Arabia. Their diverse expertise contributes to a multidisciplinary approach towards addressing anemia and malaria among children in Senegal. Overall, this research highlights the importance of leveraging machine learning algorithms along with comprehensive data analysis to improve healthcare outcomes for children suffering from anemia and malaria.