With the advent of the Covid-19 virus in early 2020 and the worldwide spread of the disease, various attempts have been made to identify and classify patients infected by COVID-19. According to the latest information in the protocol provided by the ministry of Health and Medical Treatment of Iran, patients' statuses are divided into four phases. Each phase of the disease has its own characteristics. In this study, information about patients with Covid-19 are collected by physicians specialized in infectious diseases. Patients' characteristics are classified based on clinical symptoms, laboratory parameters, and radiological images.In the proposed method, patients are classified according to their features, without supervision, and labels. The obtained results are compared with physicians' diagnosis. The results have revealed that the accuracy of the self-organized mapping is 92.5%. In addition, after clustering, the most important features of clusters are extracted by using the PCA method. After analysis and classification, the most important common features which can distinguish considered patients from other patients are: age, lung involvement and SPO2. Based on these features, the initial screening of patients can be performed with a high reliability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.