Clustering Data Pasien Covid Berdasarkan Usia dan Gejala Menggunakan Algoritma K-Means

Abstract

The case of COVID-19 is familiar to everyone's ears, but there are still a lot of people who don't care about the importance of maintaining health protocols because of the lack of education about the COVID-19 virus. The increase in cases of covid-19 is getting higher from year to year with increasingly diverse patient symptoms, therefore researchers are interested in conducting research on grouping covid patients based on age and symptoms using the k-means algorithm clustering method. Rapidminer 5 is an application used to process patient data. covid-19, but before processing the data, several processes and stages will be carried out including data cleaning, data selection, integration, transformation until the data is ready to be processed using the rapidmider application. From the result obtained cluster 1 wich amounted to 866 items it was certain that it consisted of patients aged 42-81 years with 50 deaths, while in the cluster 2 wich amounted to 1566 items with an age range of 1-41 years with 16 death. The k-means algorithm clustering method is the most appropriate solution for processing covid patient data. -19, this is because the level of accuracy produced is quite effective. The results obtained in grouping Covid-19 patient data using the k-means algorithm can be used as evaluation material by the government, especially the East Lombok District Health Office in dealing with cases of the increasingly high spread of COVID-19.