The continuous mutation of COVID-19 generates new virus variants with nearly identical symptoms, such as sneezing, runny nose, sore throat, cough, fever, loss of taste and smell, and shortness of breath. Since the emergence of this virus in Indonesia, there still needs to be more research on the symptoms caused by the different COVID-19 variants, leaving the public with minimal information that may result in inappropriate early treatment, inefficient costs, and insufficient recovery time. This study aimed to classify COVID-19 patient data into two clusters based on the severity of the symptoms experienced by patients: the confirmed cluster and the unconfirmed cluster. Using Fuzzy C-Means, patient data will be clustered into two confirmed and unconfirmed clusters of covid 19 disease as the initial step in the research phase. The results of this study are anticipated to provide information on variations in the severity of symptoms among infected patients, thereby enhancing the precision of early diagnosis and treatment. The resulting clustering model is based on data collection and processing outcomes using Python and the Fuzzy C-Means algorithm, which is based on experimentation.
 Keywords: Cluster, COVID-19, Fuzzy C-Means.