Study on DRG grouping of acute myeloid leukemia based on decision tree model
10.3760/cma.j.cn111325-20221017-00878
- VernacularTitle:基于决策树模型的急性髓系白血病DRG分组研究
- Author:
Ni CHI
1
;
Xiaoxian TU
;
Xiaolan LIAN
Author Information
1. 福建医科大学附属协和医院病案管理与统计室，福州 350001
- Keywords:
Diagnosis-related groups;
Acute myeloid leukemia;
Hospitalization costs;
Influencing factors;
Decision tree model
- From:
Chinese Journal of Hospital Administration
2023;39(2):97-101
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To explore the influencing factors of hospitalization cost of acute myeloid leukemia, to group the cases based on decision tree model and to provide reference for improving the DRG management in this regard.Methods:Homepage data were retrieved from the medical records with acute myeloid leukemia as the main diagnosis (the top four ICD codes were C92.0, C92.4, C92.5, and C93.0). These patients were discharged from the clinical hematology department of the Fujian Institute of Hematology from January 2020 to December 2021. Then the influencing factors of hospitalization expenses were identified using Wilcoxon rank sum test or Kruskal-Wallis rank sum test and multiple linear stepwise regression analysis, with such factors used as classification nodes. The decision tree model of χ2 automatic interactive testing method was used to group the cases so included. At the same time, the included cases were grouped according to the trial run C-DRG version in Fujian province, for comparison of the differences between the two grouping methods. Results:The length of stay, the type of treatment, whether associated complications and age of patients were found as the influencing factors for the hospitalization costs of patients with acute myeloid leukemia, and such factors were included in the decision tree model to form 9 case mixes. The variance reduction of this model was 75.77%, featuring a high inter-group heterogeneity, and the coefficient of variation was 0.33-0.61, featuring a low in-group difference. The patients were divided into two groups according to the C-DRG version in Fujian province. The variance reduction of this method was 27.57%, featuring a low inter-group heterogeneity, and the coefficients of variation were 0.59 and 1.25, featuring high in-group difference.Conclusions:The cases of acute myeloid leukemia were grouped based on length of stay, type of treatment, whether accompanied by complications, and age proved reasonable enough to serve as reference for DRG management and cost control of this disease.
