Deriving rules for identifying diabetic among individuals with metabolic syndrome : 대사증후군 환자 가운데 당뇨환자를 찾기 위한 규칙 도출
Deriving rules for identifying diabetic among individuals with metabolic syndrome
- 주제(키워드) 데이터 마이닝 , 의사결정나무 , 당뇨병 , 대사증후군 , 국민건강영양조사 , Data mining , Decision tree , Diabetes , Metabolic syndrome , KHANES
- 발행기관 한국디지털정책학회
- 발행년도 2018
- 총서유형 Journal
- KCI ID ART002406200
- 본문언어 영어
초록/요약
The objective of this study is to derive specific classification rules that could be used to prevent individuals with Metabolic Syndrome (MS) from developing diabetes. Specifically, we aim to identify rules which classify individuals with MS into those without diabetes (class 0) and those with diabetes (class 1). In this study we collected data from Korean National Health and Nutrition Examination Survey and built a decision tree after data pre-processing. The decision tree brings about five useful rules and their average classification accuracy is quite high (75.8%). In addition, the decision tree showed that high blood pressure and waist circumference are the most influential factors on the classification of the two groups. Our research results will serve as good guidelines for clinicians to provide better treatment for patients with MS, such that they do not develop diabetes.
more