The global pandemic of new coronaviruses (COVID-19) has infected many people around the world and became a worldwide concern since this disease caused illness and deaths. The vaccine and drugs are not scientifically established, but patients are recovering with antibiotic drugs, antiviral medicine, chloroquine, and vitamin C. Now it is obvious to the world that a quicker and faster solution is needed for monitoring and combating the further spread of COVID-19 worldwide, using non-clinical techniques, for example, data mining tools, enhanced intelligence, and other artificial intelligence technologies. In this paper, association rule mining is developing for the frequent itemsets discovery in COVID-19 datasets, and the extraction of effective association relations between them. This is done by demonstrates the analysis of the Coronavirus dataset by using the Apriori_Association_Rules algorithm. It involves a scheme for classification and prediction by recognizing the associated rules relating to Coronavirus. The major contribution of this study employment determines the effectiveness of the Apriori_Association_Rules algorithm towards a classification of medical reports. The experimental results provide evidence of the Apriori_Association_Rules algorithm regarding the execution time, memory consumption, and several associated rules that reflect its potential applications to different contexts. Therefore, the Apriori_Association_Rules algorithm will be very useful in healthcare fields to demonstrate the latest developments in medical studies fighting COVID-19.