Prediction of Covid-19 patients states using Data mining techniques

Alsmadi, T.; Alqudah, N.; Najadat, H.

Covid-19 is an infectious disease caused by a newly discovered coronavirus. It was first identified in several people with symptoms of pneumonia in Wuhan, Hubei Province. Given the scale of the epidemic and its rapid spread, and given that there is currently no vaccine for the virus, health care workers need support, as it can sometimes be challenging to predict the patient's condition. This problem can be solved through data mining techniques. Anticipating recovery situations is essential in countries seeking to contain the virus, and these predictions can help public health experts track positive citizens of COVID-19, increase doctors ability to predict the general perception of the course of events over a period, and assess patients at early risk building on approaches New based on results data. This paper discusses supervised learning on the COVID-19 Corona Virus India dataset in particular, which contains 3,799 patients, which used to classify the patient data of COVID-19 into two types, recovered and deceased. Classification approaches have been used, Including Decision tree (DT), Support vector machine support (SVM), Logistic regression (LR), Random forest (RF), k-nearest neighbors (KNN), Naïve Bayes (NB), and Artificial Neural Network (ANN) model in the patient dataset, and choosing the best method based on the accuracy, precision and recall withhold-out or cross-validation. © 2021 IEEE.