Àá½Ã¸¸ ±â´Ù·Á ÁÖ¼¼¿ä. ·ÎµùÁßÀÔ´Ï´Ù.
KMID : 1002520160100030063
Korean Journal of Health Service Management
2016 Volume.10 No. 3 p.63 ~ p.74
Development of Healthcare Data Quality Control Algorithm Using Interactive Decision Tree : Focusing on Hypertension in Diabetes Mellitus Patients
Hwang Kyu-Yeon

Lee Eun-Sook
Kim Go-Won
Hong Seong-Ok
Park Jung-Sun
Kwak Mi-Sook
Lee Ye-Jin
Lim Chae-Hyeok
Park Tae-Hyun
Park Jong-Ho
Kang Sung-Hong
Abstract
Objectives : There is a need to develop a data quality management algorithm to improve the quality of healthcare data using a data quality management system. In this study, we developed a data quality control algorithms associated with diseases related to hypertension in patients with diabetes mellitus.

Methods : To make a data quality algorithm, we extracted the 2011 and 2012 discharge damage survey data from diabetes mellitus patients. Derived variables were created using the primary diagnosis, diagnostic unit, primary surgery and treatment, minor surgery and treatment items.

Results : Significant factors in diabetes mellitus patients with hypertension were sex, age, ischemic heart disease, and diagnostic ultrasound of the heart. Depending on the decision tree results, we found four groups with extreme values for diabetes accompanying hypertension patients.

Conclusions : There is a need to check the actual data contained in the Outlier (extreme value) groups to improve the quality of the data.
KEYWORD
Data Mining, Data Quality Management Algorithm, Outlier Detection Method, Diabetes Mellitus, Hypertension
FullTexts / Linksout information
Listed journal information
ÇмúÁøÈïÀç´Ü(KCI)