AI-driven early diagnosis of Lassa fever: Development of an XGBoost-based predictive web application

Introduction: Lassa fever, a viral hemorrhagic disease endemic to West Africa, poses a serious public health threat due to high fatality rates, diagnostic delays, and nonspecific symptoms. In over 70% of confirmed cases, diagnosis occurs after Day 6 of symptom onset, often when complications have already developed (Nigeria Centre for Disease Control, 2021). Methods: A simulation-based approach using supervised machine learning was applied. A synthetic dataset of 10,000 pseudopatients was generated, modeling real-world clinical symptoms and physiological indicators from Lassa fever-endemic populations. Each record was labeled as either ‘positive’ or ‘negative’ based on a predefined risk scoring algorithm. The dataset was split into training (80%) and testing (20%) subsets. Four Machine learning models: Logistic Regression, Random Forest, Support Vector Machine, and XGBoost were trained and evaluated using accuracy, precision, recall, and F1-score. Results: Out of 10,000 pseudopatients, 4,873 (48.73%) were classified as Lassa fever positive. Among all models, XGBoost demonstrated the best performance: 94.80% accuracy, 94.50% precision, 95.20% recall, and 94.85% F1-score. This model was selected for deployment in a web-based early diagnostic system. Conclusion: Machine learning integration into frontline health systems can significantly enhance early detection, reduce diagnostic delays, and improve outbreak response in Lassa fever-endemic regions.