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.
OBJECTIVES To determine the impacts of Diagnosis-Related Groups/Prospective Payment System (DRG/PPS) on the quality of care in cases of Cesarean section and to describe the policy implications for the early stabilization of DRG/PPS in Korea. METHODS: Data was collected from the medical records of 380 patients who had undergone Cesarean sections in 40 hospitals participating in the DRG/PPS Demonstration Program since 1999. Cesarean sections were performed in 122 patients of the FFS(Fee-For-Service) group and 258 patients of the DRG/PPS group. Measurements of quality used included essential tests of pre- and post-operation, and the PPI(Physician Performance Index) score. The PPI was developed by two obstetricians. RESULTS: Univariate analysis demonstrated significant differences in PPI scores according to the payment systems. With respect to the mean of PPI scores, a higher score was found in the DRG/PPS group than in the FFS group. However, the adjusted effect did not show significant differences between the FFS group and the DRG/PPS group. CONCLUSION: This study suggested that the problem of poor quality may not be related to the implementation of DRG/PPS in Cesarean section. However, this study did not consider the validity and reliability of the process measurement, and it did not exclude the possibility of data omission in medical records.