Lassa Fever Predictive Model Using Machine Learning Techniques
Lassa Fever, a severe hemorrhagic fever caused by the Lassa virus, is notably prevalent in West Africa and can be fatal if not managed properly. Effective outbreak control and mitigation rely heavily on early detection. This study introduces a predictive model for forecasting Lassa Fever using machine learning techniques. The research employs an extensive dataset that includes epidemiological and environmental data collected over multiple years to construct a reliable predictive model. Several machine learning algorithms, such as Random Forest, Support Vector Machines (SVM), and Gradient Boosting, are utilized to analyze historical data and predict potential Lassa Fever outbreaks. To improve model accuracy and minimize false positives, feature engineering and data preprocessing methods are applied. The dataset was divided into 80% for training and 20% for testing, with various algorithms—including SVM, K-Nearest Neighbor, Naïve Bayes, and Logistic Regression—tested to build the predictive models. The performance of these models was assessed using metrics like accuracy, precision, recall, and F1 score. The SVM model demonstrated the highest performance, achieving accuracy, precision, and F1 scores of 90%, 91%, and 96%, respectively. Consequently, SVM was selected as the preferred algorithm for this research. The study recommends the use of this model in Nigeria's medical industry to enhance diagnostic speed and reduce medical errors in healthcare settings. Keywords: Lassa Fever, Predictive Model, Machine Learning, Support Vector Machines (SVM), and Healthcare Diagnostics
Authors
- Shehu BAKARI
Institutions
- Modibbo Adama University of Technology (NG)
Publication Details
- Journal
- INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
- Published
- 2026-11-13
- DOI
- https://doi.org/10.56201/ijcsmt.v10.no4.2024.pg145.173
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00