Predicting Corona Virus Affected Patients Using Supervised Machine Learning

Abstract

The world is infected from the deadliest pandemic disease humankind has ever seen. Several medical practitioners have been encountered with the corona virus and are constantly losing their lives in the fight. Hence, the main objective of this research work is to characterize the clinical features of the patients and construct a novel dataset for machine learning to classify them accurately prior to treatment. The positive patients can be identified on many characteristics and the principle data for this research is considered on the basis of the exploratory analysis done on the various risk factors that is also associated with the mortality in the hospitals. As an outcome, this article presents a supervised machine learning model incorporating the insights, symptoms and classification of the corona virus infected person. The proposed model and the dataset are tested against six well known classifiers on various levels of cross folding and percentage splits. The proposed dataset is also tested against the actual patient records and was found that the model accurately categorizes them prior to their treatment. The experimental results for proposed techniques showed higher performance and better accuracy further creating an impact on then identification of corona virus patients.