Due to the rapid development of database technology and the rapid development of a large amount of memory, the storage and processing capabilities of data are continuously enhanced. However, in the face of massive data, how to use these raw data efficiently, analyze it, and discover useful information from these data is particularly necessary. Because pulpitis is a common disease, there will be some clinical complications. Therefore, an in-depth understanding of its etiology can lay the foundation for clinical treatment. This paper attempts to use data mining technology to find rules, and applies decision tree technology to the etiological analysis of clinical pulpitis, in order to discover the etiology from a large number of clinical data, so as to provide a scientific basis for clinical prevention and treatment. On this basis, combined with the maximum probability algorithm of DBSCAN, rules, cases and mixed recommendation modes based on disease diagnosis ontology are given to recommend patients. Using the decision tree technology in data mining to analyze the problem, a decision tree model based on the diagnosis results of the problem is obtained, and the accuracy of the decision tree is judged by saving the training set and the test set. Then, through the improvement of the method, the accuracy of the method is further improved, and the correctness before and after the modification is compared. The test results show that the method has good accuracy and good practical value.