Data Mining in Oral Medicine Using Decision Trees

Data mining has been used very frequently to extract hidden information from large databases. This paper suggests the use of decision trees for continuously extracting the clinical reasoning in the form of medical expert's actions that is inherent in large number of EMRs (Electronic Medical records). In this way the extracted data could be used to teach students of oral medicine a number of orderly processes for dealing with patients who represent with different problems within the practice context over time. Keywords—Data mining, Oral Medicine, Decision Trees, WEKA. ATA mining has recently become very popular due to the emergence of vast quantities of data. In this paper, potential pitfalls and practical issues about data mining in oral medicine are discussed. Theoretical education in oral medicine to dental students is usually given through lectures, books and scientific papers. Text books often present a small number of cases for each diagnosis. Students may therefore receive information that does not reflect the reality a clinician in oral medicine encounters in daily practice. The learning that comes with experience from treatment outcomes may therefore be missing when the student graduates. mEduWeb is a program that was written and designed to give students the possibility to study oral medicine through a web interface (1). mEduWebII used the Medview database which contains data from several thousand patient examinations (1). The purpose of our work has been to seek improvements in the current mEduWebII program or, to be more specific, improvement of step-wise exercises in mEduWebII. Step-wise exercises present an orderly process for dealing with a patient who represents with a problem. The problem with step-wise exercises is that the students learn with one predefined structured thinking process for solving one type of problem. This paper identifies whether decision trees could be used for continuously extracting clinical reasoning in the form of medical expert's action that is inherent in large number of EMRs. In this way, the student would be taught a number of