Development of a Malaria Progression Prediction System with Artificial Neural Networks (ANN) and Support Vector Machines (SVM)

Abstract

Malaria has been a major worldwide health problem, especially in areas with low availability of healthcare resources. Delaying intervention frequently results in higher fatality rates. This study aims to develop a Malaria Progressive Prediction System (MPPS) using advanced machine learning methods, specifically Support Vector Machine (SVM) and Artificial Neural Network (ANN), to address this important issue. A large Kaggle dataset containing clinical and laboratory data from malaria patients at different phases of the illness is used in this study. Multiple layers of linked artificial neurons are used to build the artificial neural network (ANN), which uses a backpropagation method for training. In contrast, the SVM approach discovers the optimal hyperplane for classification by transforming input data into a multidimensional space through supervised learning. The Malaria Progressive Prediction System (MPPS) continuously showed during the performance evaluation that the Artificial Neural Networks (ANN) model outperformed the Support Vector Machine (SVM). The ANN model had greater precision, accuracy, recall, and F1 score. This produces results that demonstrate that the ANN model is highly efficient in forecasting malaria progression. It outperforms SVM in accuracy and reliability, confirming its superiority in this important healthcare application.