基于决策树模型指导社区获得性肺炎医疗费用管理的研究  

The Investigation of CHAID Decision Tree Algorithm in Managing Medical Expenses for Community-acquired Pneumonia

作　　者：陈文喧 伍靓靓 方向韶[1] CHEN Wen-xuan;WU Liang-liang;FANG Xiang-shao(Department of Emergency Medicine,Sun Yat-sen Memorial Hospital of Sun Yat-sen University,510120)

机构地区：[1]中山大学孙逸仙纪念医院急诊科,510120

出　　处：《岭南急诊医学杂志》2021年第5期475-477,共3页Lingnan Journal of Emergency Medicine

摘　　要：目的:以社区获得性肺炎(CAP)为代表性疾病,探索DRGs分组方案管理医疗费用的合理性和可行性。方法:收集中山大学孙逸仙纪念医院2016年1月至2018年12月主要诊断为"社区获得性肺炎"患者2256例,通过分析CAP患者住院费用的影响因素,利用卡方自动交互检验(CHAID)决策树建立DRGs分组方案,评价其合理性和可行性。结果:单因素分析显示住院期间进行抢救,有手术操作及合并重要并发症是CAP住院费用的主要影响因素。DRGs分组方案可合理将2256例CAP患者划分为6组,各组组间异质性和组内同质性评价效果强。结论:通过CHAID决策树模型建立的疾病DRGs病例组合方案,可对特定疾病的住院费用进行精细化管理,有望为优化医疗资源分配提供理论依据。Objective:This study explored the rationality and feasibility of diagnosis related groups(DRGs)scheme in managing medical expenses by taking community-acquired pneumonia(CAP)as representative disease. Methods:Totally 2256 patients from Sun Yat-sen Memorial Hospital of Sun Yat-sen University from January 2016 to December 2018 mainly diagnosed as CAP were enrolled. Chi-square Automatic Interaction Detector(CHAID)decision tree algorithm was used for DRGs grouping. Results:One-way analysis of variance indicated that rescue,operation,severe complications/coexisting conditions were the main factors that determining the cost of CAP. The patients were reasonably subdivided into6 groups with the CHAID decision tree algorithm. The intergroup heterogeneity and intragroup homogeneity were provedwith satisfaction. Conclusion:The DRGs grouping of a specific disease could be established with the aid of CHAID decision tree algorithm,which allow for accuracy management of medical expenses andprovide theoretical basis for optimizing medical resource allocation.

关 键 词：社区获得性肺炎 疾病诊断相关组 卡方自动交互检验决策树 

分 类 号：R563.1[医药卫生—呼吸系统]