基于CHAID算法的肝癌患者住院费用DRGs分组及超限费用影响因素研究

Study on DRGs Grouping and Influencing Factors of Hospitalization Cost of Liver Cancer Patients based on CHAID Algorithm

目的研究某三甲医院肝癌患者住院费用的疾病诊断相关分组(DRGs),为制定肝癌患者住院费用标准以及实施DRG付费提供依据。方法采用决策树模型CHAID算法建立肝癌患者的DRGs病例组合,采用灰色关联分析费用超标患者的住院费用影响因素。结果样本病例共形成8个DRGs分组,8个分组的总体方差减少系数RIV值为87.8%,组间异质性较高且各组的变异系数CV值均小于1,各组内变异程度较小,说明分组效果较好。灰色关联分析结果显示,药费(0.701)、治疗费(0.682)及耗材费(0.681)是影响费用超标患者住院费用的重要因素。结论肝癌病例分组合理,药费是线外患者住院费用的最重要影响因素。

Objective To study the DRGs case combination scheme of the inpatient cost of liver cancer patients in a third grade A hospital,and to provide basis for the formulation of the inpatient cost standard of liver cancer patients and the implementation of DRG payment.Methods Decision tree model CHAID algorithm was used to establish DRGs case combination of liver cancer patients,and grey correlation analysis was used to analyze the influencing factors of hospitalization expenses of patients with excessive expenses.Results A total of 8 DRGs groups were formed in the sample cases.The RIV value of the total variance reduction coefficient of the 8 groups was 87.8%,the inter-group heterogeneity was high,and the CV value of the coefficient of variation of all groups was less than 1,indicating that the degree of variation within each group was small,indicating that the grouping effect was good.The results of grey correlation analysis showed that drug cost(0.701),treatment cost(0.682)and consumables cost(0.681)were the important factors affecting the hospitalization cost of patients with excessive expenses.Conclusion Liver cancer cases are grouped reasonably,and drug cost is the most important factor influencing the hospitalization cost of out-of-line patients.