.png){kind=icon}
.png){kind=icon}
Return
Ensemble Machine Learning for Malaria Diagnosis in Resource-Limited Settings Using Clinical and Demographic Features
.png){kind=icon}
OA
AI
P
H
F
DOI：10.3390/idr18040072.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Background: Sub-Saharan Africa suffers the greatest impact of malaria, with the 2024 Health Organization (WHO )report stating that the region represents 94% of global cases and 95% of deaths. Challenges in malaria elimination stem from weak health systems and limitations of traditional diagnostic methods like microscopy and malaria Rapid Diagnostic Tests (mRDTs), which result in missed diagnoses, delays in treatment, and preventable fatalities in resource-limited settings. This paper addresses these diagnostic limitations by developing and systematically evaluating a machine learning (ML) framework for malaria diagnosis that leverages routine clinical symptoms and demographic information tailored for these environments. Methods: Examining 637 patient records from Gutu Mission Hospital and Gweru Provincial Hospital in Zimbabwe, the research analyzed clinical symptoms (fever, chills, abdominal pain, headache, diarrhea) and demographic data (age, gender, residence, travel history). Data preprocessing involved addressing class imbalance with the Synthetic Minority Oversampling Technique (SMOTE) and employing Recursive Feature Elimination (RFE) for feature selection. Seven ML models were trained: Logistic Regression, Random Forest, Decision Trees, Gradient Boosting, K-Nearest Neighbor, Naive Bayes, and XGBoost. These individual models were used to construct ensemble models like Bagging, Stacking, Soft Voting, and AdaBoost. Performance metrics included accuracy, precision, confusion matrices, recall, F1 score, and AUC-ROC. Results: Statistically significant predictors for malaria included chills (p = 0.001), fever (p = 0.003), diarrhea (p = 0.01), and abdominal pain (p < 0.001), with travel history showing significance among demographic factors (p = 0.02). The stacking ensemble model yielded superior performance, achieving an accuracy of 0.96, precision of 0.95, recall of 0.98, F1 score of 0.96, and AUC-ROC of 0.98. Conclusions: This study underscores the potential of ML, particularly ensemble techniques, to enhance malaria management in resource-limited settings, providing a scalable and cost-effective diagnostic alternative that utilizes accessible clinical and demographic data, thereby supporting healthcare workers and control programs in areas where traditional methods are inadequate.
Keywords:
malaria diagnosis
machine learning
ensemble models
resource-limited settings
Journal
IF:
2.4
Papers:
1.4K
Citations:
957
Organization
Cited Papers