Abstract: Objective To study the feasibility of using rough set and support vector machines to detect Parkinson disease. Methods The reduction algorithm based on the importance of the attributes in the rough set theory was used to reduce the common diagnosis features in the clinical practice. The support vector machines were applied for classification with the linear, polynomial and RBF kernel, and the Results were compare with that of BP neural network. Results The algorism combined attributes reduction and support vector machines appeared the highest accuracy of 92.71% in the classification, which seemed greater advantage in accuracy and stability than BP neural network. Conclusion Improving the accuracy of the classification as well as saving the resources, rough set and support vector machines are proved to be an effective method to assist the clinical diagnosis of Parkinson disease.

Key words: rough set, attributes reduction, support vector machines, Parkinson disease