Research on DRGs grouping for patients with chronic obstructive pulmonary disease based on quantile regression and decision tree model
Wu Li1, Lü Zhijie2, Lu Hanti1, Huang Sijia1, Zhou Penglei1
1 The First Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou 310006, China;
2 Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou 310020, China
Abstract：Objective To explore the DRGs grouping and hospitalization cost standard for patients with chronic obstructive pulmonary disease (COPD), and to provide support for relevant hospital managers to formulate targeted control measures and improve the system.Methods The first page data of COPD patients′ medical records from a tertiary hospital from 2018 to 2020 were selected. Multiple linear regression, quantile regression and decision tree model were used for case combination analysis.Results Totally 1 929 patients with COPD were included in this study. The results of multiple linear regression model and quantile regression model showed that the hospitalization days, age, payment method, source of patients and complications/comorbidities were the main factors influencing the hospitalization cost of patients with COPD (P<0.05). Taking hospitalization days as the influence variable, and age, complications/comorbidities, source of patients and payment method as 4 classification nodes into decision tree model, 5 DRGs combinations were formed with the corresponding standard of hospital expenses and the weight of disease types. The standard hospitalization expenses of each group were 17 814.40 yuan, 12 138.80 yuan, 10 402.07 yuan, 10 144.50 yuan and 7 954.49 yuan, and the disease weight coefficients were 1.36, 0.93, 0.79, 0.77 and 0.61 respectively.Conclusion It is beneficial to control the inpatient cost of this disease, reduce the economic burden of patients, and provide the basis for the reform of medical expense payment mode by establishing the standard of inpatient cost and the weight of disease.
吴丽，吕志杰，卢汉体，黄思佳，周鹏蕾. 基于分位数回归与决策树模型的慢性阻塞性肺疾病患者DRGs分组研究[J]. 中国医院统计, 2022, 29(1): 42-46.
Wu Li, Lü Zhijie, Lu Hanti, Huang Sijia, Zhou Penglei. Research on DRGs grouping for patients with chronic obstructive pulmonary disease based on quantile regression and decision tree model. journal1, 2022, 29(1): 42-46.
［1］FANG L W, GAO P, BAO H L, et al. Chronic obstructive pulmonary disease in China: A nationwide prevalence study［J］. Lancet Respir Med, 2018, 6(6):421-〖JP2〗430.DOI:10.1016/S2213-2600(18)30103-6.
［2］苏飞月，符美玲，谭慭莘，等．基于分位数回归与决策树模型的跌倒患者住院费用影响因素分析［J］．中国卫生统计，2021，38(1)：67-72．DOI:10.3969/j.issn.1002-3674.2021.01.018.
［3］孙菲，韩俊洋，张文倩，等．基于决策树模型的急性心肌梗死病例组合研究［J］．中国病案，2021，22(3)：75-79．
［4］金萍妹，华伟，陈洁，等．基于疾病诊断相关组法制定单病种住院费用标准的研究［J］．中国卫生经济，2017，36(2)：26-28．DOI:10.7664/CHE20170207.
［5］程亮亮，段占祺，张娟，等. 呼吸系统疾病患者住院费用的DRGs研究［J］. 中华医院管理杂志,2017(8):591-595.DOI:10.3760/cma.j.issn.1000-6672.2017.08.009.
［6］国家医疗保障局. 关于印发疾病诊断相关分组（DRG）付费国家试点技术规范和分组方案的通知［A/OL］.（2019-10-24）［2021-10-03］.http://www.nhsa.gov.cn/art/2019/10/24/art_37_1878.html.
［7］OLSEN M A, TIAN F, WALLACE A E, et al. Use of quantile regression to determine the impact on total health care costs of surgical site infections following common ambulatory procedures［J］. Ann Surg, 2017, 265(2):331-339.DOI:10.1097/SLA.0000000000001590.
［8］吴俊霞，李育梅，黄松平，等．慢性乙型病毒性肝炎DRGs分组研究［J］．中国卫生统计，2020，37(6)：905-907．DOI:10.3969/j.issn.1002-3674.2020.06.027.
［9］王芳，孙红霞．疾病诊断相关组方法在妊娠分娩产褥期疾病中的应用［J］．中国卫生统计，2019，36(1)：108-110．
［10］徐梦秋，丁丽萍．前列腺癌患者住院费用的疾病诊断相关分组研究［J］．中国医院统计，2020，27(5)：416-419．DOI:10.3969/j.issn.1006-5253.2020.05.008.
［11］邵慧丽，宁传英．基于ECHAID算法胆囊结石患者DRGs分组研究［J］．中国卫生统计，2019，36(4)：554-555．
［12］许琼琼，肖静，沈康，等．基于决策树模型食管癌病例组合研究［J］．中国卫生统计，2016，33(4)：563-566．
［13］黄利娟，查〖JP2〗君敬，毛以成，等．基于DRGs组合方式制定子宫平滑肌瘤患者住院费用标准的分析［J］．中国病案，2017，18(6)：64-66．
