Efficient DRG Fraud Candidate Detection Method Using Data Mining Techniques.
- Author:
Duho HONG
1
;
Jung Kyu LEE
;
Min Woo JO
;
Kidong PARK
;
Sang Il LEE
;
Moo Song LEE
;
Chang Yup KIM
;
Yong Ik KIM
Author Information
1. Department of Health Policy and Management, Seoul National University College of Medicine, Korea.
- Publication Type:Original Article
- Keywords:
Diagnosis-Related Groups;
Fraud;
Decision trees;
Neural networks
- MeSH:
Adenoidectomy;
Appendectomy;
Cesarean Section;
Data Mining*;
Decision Trees;
Diagnosis-Related Groups*;
Female;
Fraud*;
Hernia, Femoral;
Logistic Models;
Methods*;
Pregnancy;
Tonsillectomy;
Trees;
Vitrectomy
- From:Korean Journal of Preventive Medicine
2003;36(2):147-152
- CountryRepublic of Korea
- Language:Korean
-
Abstract:
OBJECTIVES: To develop a Diagnosis-Related Group (DRG) fraud candidate detection method, using data mining techniques, and to examine the efficiency of the developed method. METHODS: The study included 79, 790 DRGs and their related claims of 8 disease groups (Lens procedures, with or without, vitrectomy, tonsillectomy and/or adenoidectomy only, appendectomy, Cesarean section, vaginal delivery, anal and/or perianal procedures, inguinal and/or femoral hernia procedures, uterine and/or adnexa procedures for nonmalignancy), which were examined manually during a 32 months period. To construct an optimal prediction model, 38 variables were applied, and the correction rate and lift value of 3 models (decision tree, logistic regression, neural network) compared. The analyses were performed separately by disease group. RESULTS: The correction rates of the developed method, using data mining techniques, were 15.4 to 81.9%, according to disease groups, with an overall correction rate of 60.7%. The lift values were 1.9 to 7.3 according to disease groups, with an overall lift value of 4.1. CONCLUSIONS: The above findings suggested that the applying of data mining techniques is necessary to improve the efficiency of DRG fraud candidate detection.
