[1]张盼盼),田 晶),杨 弘),等.基于随机森林的慢性心力衰竭患者报告结局量表的预后评估价值[J].郑州大学学报(医学版),2020,(06):786-790.[doi:10.13705/j.issn.1671-6825.2020.05.115]
　ZHANG Panpan),TIAN Jing),YANG Hong),et al.Prognostic value of patient-report outcome scale with heart failure based on random forest[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2020,(06):786-790.[doi:10.13705/j.issn.1671-6825.2020.05.115]
点击复制

基于随机森林的慢性心力衰竭患者报告结局量表的预后评估价值()
分享到：

《郑州大学学报(医学版)》[ISSN:1671-6825/CN:41-1340/R]

卷:
期数:
2020年06期
页码:
786-790
栏目:
论著
出版日期:
2020-11-20

文章信息/Info

Title:
Prognostic value of patient-report outcome scale with heart failure based on random forest
作者:
张盼盼1); 田 晶2); 杨 弘1); 李晨昊1); 闫晶晶1); 王 可1); 韩 嫱1); 张 青3); 韩清华2); 张岩波1)
1)山西医科大学卫生统计教研室 太原 030001 2)山西医科大学第一附属医院心内科 太原 030001 3)山西医科大学第一临床医学院 太原 030001
Author(s):
ZHANG Panpan1); TIAN Jing2); YANG Hong1); LI Chenhao1); YAN Jingjing1); WANG Ke1); HAN Qiang1); ZHANG Qing3); HAN Qinghua2); ZHANG Yanbo1)
1)Department of Health Statistics,Shanxi Medical University,Taiyuan 030001 2)Department of Cardiology,the First Affiliated Hospital,Shanxi Medical University,Taiyuan 030001 3)The First Clinical Medical College,Shanxi Medical University,Taiyuan 030001
关键词:
随机森林;  心力衰竭;  患者报告结局量表;  预后
Keywords:
random forest;  heart failure;  patient-reported outcome;  prognosis
分类号:
R181.2; R541
DOI:
10.13705/j.issn.1671-6825.2020.05.115
摘要:
目的:探讨患者报告结局量表在慢性心力衰竭预后评估中的应用价值。方法:选择2017年5月至2019年3月住院确诊为慢性心力衰竭的629例患者为研究对象,对患者进行患者报告结局问卷调查,并随访其出院后1 a内主要不良心血管事件的发生,构建随机森林模型,用净重分类改善指数、整体鉴别指数以及受试者工作特征曲线,比较患者报告结局对预后模型的增加价值。结果:纳入PRO数据后模型的灵敏度为70.0%,特异度为90.8%,AUC值为0.804,增加了0.226; 以未纳入PRO数据的预测模型为参照得出净重分类改善指数为0.452,模型正向改善,整体鉴别指数为0.172,经检验,改善程度均有统计学意义(P<0.05)。结论:患者报告结局量表在慢性心力衰竭预后研究中有较高的应用价值。
Abstract:
Aim:To explore the application value of patient-report outcome scale in the study of prognosis of heart failure.Methods:A total of 629 patients with heart failure diagnosed in the hospital from May 2017 to March 2019 were selected.The patients were investigated by patient-reported outcomes scale.The occurrence of major adverse cardiovascular events within one year follow-up after discharge was recorded.A random forest model was constructed,and the prognostic value of the model was evaluated by net reclassification improvement,integrated discrimination improvement and receiver operator characteristic curve.The added value of the patient-reported outcomes to the prognostic model was compared.Results:After the inclusion of PRO data,the sensitivity of the model was 70.0%,the specificity was 90.8%,and the AUC value was 0.804,which increased by 0.226.With reference to the prediction model that did not include PRO data,the net reclassification improvement was 0.452,the model was positively improved,and integrated discrimination improvement was 0.172,which was statistically significant(P<0.05).Conclusion:The patient-report outcome scale has high application value in evaluating the prognosis of patients with heart failure.

参考文献/References:

[1] 中华医学会心血管病学分会心力衰竭学组,中国医师协会心力衰竭专业委员会,中华心血管病杂志编辑委员会.中国心力衰竭诊断和治疗指南2018[J].中华心血管病杂志,2018,46(10):760
[2] 张海涛,杜雨,曹芳芳,等.低心排血量综合征中国专家共识[J].解放军医学杂志,2017,42(11):933
[3] AMBROSY AP,FONAROW GC,BUTLER J,et al.The global health and economic burden of hospitalizations for heart failure: lessons learned from hospitalized heart failure registries[J].J Am Coll Cardiol,2014,63(12):1123
[4] 吕静,薛江平,罗艳虹,等.慢性心衰PRO量表条目的初步筛选[J].中国卫生统计,2014,31(3):379
[5] TIAN J,XUE J,HU X,et al.CHF-PROM: validation of a patient-reported outcome measure for patients with chronic heart failure[J].Health Qual Life Outcomes,2018,16(1):51
[6] Fernandez-Delgado M,Cernadas E,Barro S,et al.Do we need hundreds of classifiers to solve real world classification problems?[J].J Mach Learn Res,2014,15:3133
[7] Breiman L,Breiman L,Cutler RA.Random forests machine learning[J].J Clin Microbiol,2001,2:199
[8] 于莉莉,武颂文,夏结来.利用净重新分类指数与整体鉴别指数评价一种新危险因素的补充预测能力[J].中国卫生统计,2017,34(5):761
[9] 常宇飞,马剡芳,刘京鹤,等.心力衰竭患者出院后转归及影响因素分析[J].中国预防医学杂志,2016,17(11):842
[10]NAHUM J,BENSAID A,DUSSAULT C,et al.Impact of longitudinal myocardial deformation on the prognosis of chronic heart failure patients[J].Circ Cardiovasc Imaging,2010,3(3):249
[11]LAGENDIJK M,VAN EL,RICHEL C,et al.Patient reported outcome measures in breast cancer patients[J].Eur J Surg Oncol,2018,44(7):963
[12]YANG LY,MANHAS DS,HOWARD AF,et al.Patient-reported outcome use in oncology: a systematic review of the impact on patient-clinician communication[J].Support Care Cancer,2018,26(1):41
[13]刘才雄.基于多元统计方法的航空公司客户价值研究[D].杭州:浙江理工大学,2018
[14]刘云翔,陈斌,周子宜.一种基于随机森林的改进特征筛选算法[J].现代电子技术,2019,42(12):117

备注/Memo

备注/Memo:
【基金项目】国家自然科学基金项目(81872714)
【作者简介】张岩波,通信作者,男,1969年10月,博士,教授,研究方向:慢性病生命质量评价及潜在状态评估模型构建,E-mail:sxmuzyb@126.com
更新日期/Last Update: 2020-11-20