The world is currently facing many unrests and challenges due to the emergence of the COVID-19 Epidemic. The management of medical resources is considered one of the most important challenges posed by the emergence of this epidemic. The intensive care unit (ICU) plays an important role in saving the life of a COVID-19 patient, and therefore work has been done in this research to find models to predict the patient's need to enter ICU or not. The prediction models depend on Machine Learning (ML). Three models will be built to predict the state at which the patient needs to enter the ICU or not. The proposed predictor models based on three types of Supervised machine learning Naive Bayes, K -nearest neighbor (K-NN), and Support Vector Machine (SVM) according to the scarce datasets. Predictor model trained based on Extracted features from patients' X-ray images.