Prediction of Typhoid Using Machine Learning and Ann Prior to Clinical Test

Abstract

Typhoid fever is a serious and potentially fatal illness that causes a large number of deaths each year, particularly in developing countries. Early and accurate diagnosis is essential for effective treatment and to prevent the spread of the disease. In this study, we used machine learning techniques to develop a predictive model for typhoid fever. We used a dataset of 1746 entries and 29 attributes, and applied ten different algorithms to the data. Our results showed that machine learning can be effective tools for the prediction of typhoid fever, with the XGBoost classifier performing particularly well, achieving an accuracy rate of 97.87%. In addition to the XGBoost classifier, we also evaluated the performance of several other algorithms, including the Random Forest classifier, Extra Trees classifier, and Artificial Neural Network. While each of these classifiers performed well, the XGBoost classifier was found to be the most effective, with accuracy rates of 97.78% and 97.42% for the Random Forest and Extra Trees classifiers, respectively. Overall, our results demonstrate the potential of machine learning and ANNs for the prediction of typhoid fever, and suggest that these technologies could be useful tools for improving the diagnosis and treatment of this disease. Further research will be needed to explore the potential of these technologies in more detail, and to identify the most effective approaches for their implementation and deployment.