Decision Tree Approach Characterizing the Non-Examinees of Health Screening Services.
- Author:
Ae Kyung LEE
1
;
Il Su PARK
;
Sun Mi LEE
Author Information
1. National Health Insurance Corporation, Research Center.
- Publication Type:Original Article
- Keywords:
Health Screening;
Customer Relationship Management(CRM);
Data Mining;
Decision Trees
- MeSH:
Data Mining;
Decision Trees*;
Mass Screening*;
National Health Programs;
ROC Curve
- From:Journal of Korean Society of Medical Informatics
2007;13(3):271-278
- CountryRepublic of Korea
- Language:Korean
-
Abstract:
OBJECTIVE: The purpose of this study was to develop the decision tree models to classify the characteristics of those who had not undergone the health screening tests provided by the National Health Insurance Corporation. METHODS: Total of 5,102,761 subjects of health screening services in the year of 2002 was used. The data was divided into two data-sets (disease VS. non-disease group). The target variable was whether they took the health screening services. The number of input variables was 25 in total. RESULTS: The decision trees were classified into fourteen different types of non-examinees in the non-disease group and nineteen in the disease group. The ROC curve areas in the non-disease and disease groups were .761 and .714, respectively. CONCLUSION: The different types of non-examinees classified by the decision tree models would facilitate the foundation for the further analysis of individual characteristics and the effective health screening service management in future.
