Analysing the ML and DL-based Models for Predicting Malarial Fever Prior to Clinical Trial

Abstract

Malaria is a deadly disease caused by unicellular protozoan parasites of the Plasmodium genus. This disease is widespread throughout the world. Confirming the presence of parasites early on in all cases of malaria allows for the administration of species-specific antimalarial medication, which reduces mortality and points to other illnesses when the diagnosis is negative. Nonetheless, light microscopy of thin and thick PB films stained with May-Grünwald-Giemsa (MGG) remains the gold standard. Because this is a labor-intensive process that relies on the expertise of a pathologist, medical professionals in areas of the world where malaria is not common may have difficulty diagnosing cases of the disease. This study used thirteen different machine-learning models to predict malaria fever. The Gaussian NB, Logistic Regression, XGB, Bagging Classifier, Random Forest Classifier, Extra Trees Classifier, Gradient Boosting Classifier, Hist Gradient Boosting Classifier, LGBM Classifier, Decision Tree Classifier, Ada Boost Classifier, SGD Classifier, and K Nearest Neighbors (KNN) Classifier were among the models used. This study classifies malaria cases using data obtained from chest X-ray images for this study. A dataset with 1079 patient records and 23 attributes was created. These characteristics were obtained from the Kaggle repository. Out of these 23 attributes, 80% of the data were used to train the model, and the remaining 20% were used to assess the validation accuracy. It has been shown that the Gaussian NB models were the most accurate, with a 97.66% accuracy rate.