SEGMENTATION of COVID-19 POSITIVE PATIENTS REGARDING SYMPTOMS AND COMPLAINTS

Authors : Gökhan SİLAHTAROĞLU, Kevser ŞAHİNBAŞ

Pages : 37-47

Doi:10.18038/estubtda.877029

View : 14 | Download : 7

Publication Date : 2022-03-30

Article Type : Research Paper

Abstract :The COVID-19 has spread rapidly among people living in all around the world and become a global threat. COVID-19 is approaching approximately 46 million cases worldwide according to the World Health Organization insert ignore into journalissuearticles values(WHO);. There are limited number of COVID-19 test kits because of the rapid increasing cases daily. The fatality rate of ill patients with COVID-19 is very high in all around the world. Therefore, it is critical to cluster COVID-19 cases by applying clustering methods and provide the features of each. In this paper, we present symptom statistics of COVID-19 diagnosed patients to be used to foresee whether a patient will suffer through the illness severely or not. A clustering model by applying Fuzzy C-Means and PCA data reduction and visualization of data in a scatter diagram is also presented in the study. Clustering results shows patients may be segmented as risky or not in terms of the symptoms observed. We used the complaints and symptoms of 1.313 PCR-confirmed COVID-19 positive patients admitted to a university hospital in Istanbul. The findings from clustering method suggest that weakness, cough and sore throat were the most common COVID-19 symptoms and all of symptoms are separated into 3 clusters. Herein we report which symptoms are serious that may lead patients to critical situation.
Keywords : COVID 19, Coronavirus, Fuzzy C Means, Segmentation