Mining Students and Patients Data of Dentistry College in the University of Mosul

This research paper includes the design and implementation of a system for mining student and patient data at the College of Dentistry at the University of Mosul using the Microsoft SQL Server database management system to design and implement the database system and WEKA program for database mining, and the Microsoft Visual C# .NET 2012 language was used to program system interfaces. The main steps of the database included analysis, design and implementation, and the mining process included seven steps; data collection, data preprocessing, data exploration, data transformation, data modeling, evaluation, and deployment. The database mining process was divided into two parts; the first part is a smart cluster process for students of the Faculty of Dentistry for the fourth and fifth stages on laboratories (i.e. the number of chairs available for each laboratory) using three famous algorithms (Canopy, K-Means, EM), the second part is the process of classifying patients into four classes according to the type of treatment that each patient needs using three also famous algorithms (SVM, Naïve Bayes, Random Forest). ). After applying the system to the real data of the College of Dentistry at the University of Mosul, it was found that the best cluster algorithm is K-Means and the best classification algorithm is Naïve Bayes.