Optimization of Diagnosis-Related Groups for 14,246 Patients with Uterine Leiomyoma in a Single Center in Western China Using a Machine Learning Model

• DOI: 10.2147/rmhp.s442502
• Publication Date: 2024-03-01T08:20:06Z
• Authors: Yuan Ma; Li Li; Li Yu; Wei He; Ling Yi; Yuxin Tang; Jijie Li; Zhigang Zhong; Meixian Wang; Shiyao Huang; Yiquan Xiong; Pei Xiao; Yuxiang Huang
• Keywords: CHAID; Univariate analysis; Stepwise regression

Background: Uterine leiomyoma (UL) is one of the most common benign tumors in women, and its incidence gradually increasing China. The clinical complications UL have a negative impact on women's health, cost treatment poses significant burden patients. Diagnosis-related groups (DRG) are internationally recognized as advanced healthcare payment management methods that can effectively reduce costs. However, there variations design grouping rules DRG policies across different regions. Therefore, this study aims to analyze factors influencing hospitalization costs patients with optimize schemes provide insights for development localized policies. Methods: Mann–Whitney U -test or Kruskal–Wallis H was employed univariate analysis, multiple stepwise linear regression analysis utilized identify primary UL. Case combination classification conducted using exhaustive chi-square automatic interactive detection (E-CHAID) algorithm within decision tree framework. Results: Age, occupation, number hospitalizations, type medical insurance, Transfer other departments, length stay (LOS), UL, admission condition, comorbidities complications, procedure, types surgical procedures, discharge method had (P< 0.05). Among them, LOS were main By incorporating into model, divided 11 combinations. Conclusion: Hospitalization mainly related LOS. case combinations based E-CHAID scientific reasonable. Keywords: uterine leiomyoma, diagnosis-related groups,