Title: A Comparative Study Of Machine Learning Algorithms For Predictive Healthcare Systems
Authors: Balasa Jonathan Sunday, Andeze Peace Dan, Hope Rimam Bulus
Volume: 9
Issue: 5
Pages: 82-87
Publication Date: 2025/05/28
Abstract:
This study assess the comparative analysis of five machine learning algorithms Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Neural Network in the development of a predictive healthcare model using clinical data from Specialist Hospital Jalingo. The study adopted a quantitative methodology involving data preprocessing, model training, and performance evaluation using metrics such as accuracy, precision, recall, F1 score, and area under the ROC curve (AUC). Results showed that the Neural Network and Random Forest models outperformed other algorithms, achieving accuracies of 0.89 and 0.87 respectively, with corresponding AUC scores of 0.93 and 0.91. The study recommends the adoption of such models in Nigerian hospitals to improve diagnostic efficiency and support evidence-based decision-making. The research contributes to the growing body of knowledge on artificial intelligence applications in healthcare and underscores the need for data-driven innovations in resource-limited settings.