Related Experiment Video
Updated: Mar 15, 2026
Author Spotlight: Developing a Point-of-Care Hemoglobin Estimation Method for Anemia Management
Published on: January 19, 2024
Deployment of a machine learning-based predictive system for childhood diarrhea in Sub-Saharan Africa
Eliyas Addisu Taye1, Eyob Akalewold Alemu2, Halima Ayalew Kebede3
1Department of Health Informatics, College of Medicine and Health Science, University of Gondar Comprehensive Specialized Hospital, Gondar, Ethiopia. eliyasaddisu12@gmail.com.
Insights
A new machine learning model predicts childhood diarrhea in Sub-Saharan Africa (SSA) with high accuracy. This deployed tool offers a practical solution to reduce child mortality by enabling early intervention.
Area of Science:
- Public Health
- Machine Learning
- Pediatrics
Background:
- Diarrhea is a major cause of child mortality in Sub-Saharan Africa (SSA).
- Existing machine learning (ML) models for healthcare often lack scalable, real-world deployment.
- Predictive tools are needed for early intervention to combat childhood diarrhea in SSA.
Purpose of the Study:
- To develop and deploy an end-to-end machine learning framework for predicting diarrhea in children under five in SSA.
- To bridge the gap between ML research and practical public health applications.
- To create a tangible, deployable solution for aiding public health decision-making.
Main Methods:
- Utilized Demographic and Health Surveys (DHS) data from 27 SSA countries (2016-2024).
- Preprocessed data including handling missing values, feature selection, and SMOTE for class imbalance.
- Trained and optimized a Random Forest classifier using RandomizedSearchCV, deployed via a Flask-based RESTful API.
Main Results:
- The deployed Random Forest model achieved 79.6% accuracy.
- The model demonstrated a high recall of 84.1%, indicating strong effectiveness in identifying true diarrhea cases.
- Successfully created a complete pipeline from data analysis to a deployed, interactive system.
Conclusions:
- The study successfully demonstrates a complete ML pipeline from data to deployment, offering a practical solution for predicting childhood diarrhea in SSA.
- The deployed model serves as a tangible tool to aid public health decision-making and reduce child mortality.
- Future work should focus on model interpretability, scalable deployment technologies (FastAPI, Docker), and field validation with community stakeholders.
Abstract:
Diarrhea remains a leading cause of child mortality in Sub-Saharan Africa, necessitating advanced predictive tools for early intervention. Despite the growing adoption of machine learning in healthcare, gaps persist in deploying models as scalable, real-world solutions. This study developed an end-to-end machine learning framework to predict diarrhea among children under five in SSA, integrating rigorous model development with Flask-based deployment for practical use. Using nationally representative Demographic and Health Surveys (DHS) data from 27 SSA countries (2016-2024), we preprocessed data (handling missing values, feature selection, and SMOTE for class imbalance), trained a Random Forest classifier (optimized via RandomizedSearchCV), and deployed the model as a RESTful API with Flask. The final model demonstrated strong predictive power, with 79.6% accuracy and a particularly high recall of 84.1%, meaning it is exceptionally effective at identifying true diarrhea cases. Most importantly, the model is no longer just a research output; it is a deployed, interactive system ready for practical application. This work successfully demonstrates a complete pipeline from data to deployment, offering a tangible solution that can aid public health decision-making. We have proven that it is possible to close the gap between machine learning research and real-world implementation. To build on this foundation, future work should focus on enhancing the model's interpretability for health workers, adopting more scalable deployment technologies like FastAPI and Docker, and conducting rigorous field validation with community stakeholders to ensure these tools truly meet the needs of those they are designed to serve.
