文章基本信息

标题：USING DATA MINING TO DEVELOP MODEL FOR CLASSIFYING DIABETIC PATIENT CONTROL LEVEL BASED ON HISTORICAL MEDICAL RECORDS
本地全文：下载
作者：TARIG MOHAMED AHMED
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2016
卷号：87
期号：2
出版社：Journal of Theoretical and Applied
摘要：Nowadays, diabetes is considered as one of the diseases which cause more deaths than any other disease in the world. To avoid the dangerous complications of the diabetes, patients should control a blood glucose level as the HbA1c (accumulative blood glucose level for 3 months) should be less than 7%. In this paper a new predicted model has been developed by using data mining techniques. The model aims to classify the diabetic patients into two classes which are: under control (HbA1c < 7%) and out of control (HbA1c > 7%). The treatments plans for 10061 diabetic patients were used to build the model. After comprehensive survey for classification techniques, three algorithms have been selected which were NaivaeBayse, Logistic and J48. By using WEKA application, the model has been implemented. Based on the results of experiment, Logistic algorithm has been selected as best one with high accuracy rate of 74.8%. To enhance the model accuracy, the nutrition system and exercise need to be added to the dataset as future work.
关键词：Diabetes; Data Mining; Classification techniques