Mycobacterium bacteria is the cause of tuberculosis, an infectious disease that attacks the respiratory tract in humans and can easily spread through the air. In 2012, WHO data showed that tuberculosis is an infectious disease that causes the second largest health problem in the world. Tuberculosis is a disease that can attack other parts of the body as well as the lungs. The sooner a person finds out he has tuberculosis and gets tested, the more likely he will recover faster. There are many detection methods, but many are time consuming. A decision support system is needed using the WASPAS method and the CPI method which are capable of diagnosing tuberculosis. To overcome this problem. By forming a decision tree represented by rules, this decision support system implements Rank Order Centroids, one of the classification techniques in machine learning used in the data mining process. This study produces a system that is expected to make it easier for the general public to obtain timely and accurate information for diagnosing tuberculosis. A decision support system for diagnosing tuberculosis was developed as a result of this study. After being tested with 100 patient data, 50 as training data and 50 as testing data, the Confusion Matrix produces an accuracy value of 90%.