浏览全部资源
扫码关注微信
基于XGBoost的COVID-19患者重症风险早期预测模型的建立与评价
Early prediction model for disease progression of COVID-19 patients based on XGBoost: establishment and evaluation
- 陆军军医大学学报 2022年44卷第3期 页码：195-202
- 作者机构：
1.400042 重庆，陆军特色医学中心消化内科
2.400038 重庆，陆军军医大学(第三军医大学)生物医学工程与影像医学系
3.400038 重庆，陆军军医大学(第三军医大学)基础医学院学员五大队
4.430010 武汉，武汉市火神山医院感染一科
- 作者简介：
[ 刘凯军，E-mail：kliu_tmmu@126.com LIU Kaijun, E-mail: kliu_tmmu@126.com
- 基金信息：
DOI：10.16016/j.2097-0927.202107161
中图分类号： R319;R512.99收稿：2021-07-26，
修回：2021-08-24，
纸质出版：2022-02-15
- 稿件说明：
移动端阅览
王铭, 程振豪, 胡苗, 等. 基于XGBoost的COVID-19患者重症风险早期预测模型的建立与评价[J]. 陆军军医大学学报, 2022,44(3):195-202.
Ming WANG, Zhenhao CHENG, Miao HU, et al. Early prediction model for disease progression of COVID-19 patients based on XGBoost: establishment and evaluation[J]. Journal of Army Medical University, 2022, 44(3): 195-202.
王铭, 程振豪, 胡苗, 等. 基于XGBoost的COVID-19患者重症风险早期预测模型的建立与评价[J]. 陆军军医大学学报, 2022,44(3):195-202. DOI： 10.16016/j.2097-0927.202107161.
Ming WANG, Zhenhao CHENG, Miao HU, et al. Early prediction model for disease progression of COVID-19 patients based on XGBoost: establishment and evaluation[J]. Journal of Army Medical University, 2022, 44(3): 195-202. DOI： 10.16016/j.2097-0927.202107161.
摘要
目的
2
利用新型冠状病毒病(corona virus disease 2019，COVID-19)患者的临床特征数据构建XGBoost预测模型，并评价预测模型对COVID-19患者重症进展风险早期预测的效能。
方法
2
对2020年2月10日至4月5日火神山医院病案系统内经实验室确诊的COVID-19患者进行筛选，共收集347例有完整医疗信息和实验室检查结果的患者数据。首先筛选出21个具有显著性差异的指标作为训练模型的输入特征；对构建的XGBoost模型进行贝叶斯优化以调整参数，并基于特征重要性筛选出最优特征组合；进一步分析各特征数值大小对预测结果的正负影响，利用SHAP(SHapley Additive exPlanation)对各特征重要性进行量化和归因；对XGBoost预测模型进行性能评价，并将其与其他机器学习方法进行对比，讨论其优势所在。
结果
2
本研究选取21个重症组与非重症组差异显著的特征进行训练和验证。在K最邻近(k-nearest neighbor，KNN)模型中具有10个特征的最优子集获得了验证集中4个模型中曲线下面积(area under curve，AUC) 值的最高值。年龄、脉率、白细胞计数、中性粒细胞计数、C-反应蛋白、总胆红素、肌酐、D-二聚体(D-Dimer)越高，疾病重症风险越高；淋巴细胞计数、白蛋白水平越低，疾病重症风险越高。XGBoost与支持向量机的预测性能优于其他机器学习方法(在测试集上AUC值分别为0.942 0、0.959 4)，其中XGBoost训练速度明显更优。
结论
2
基于XGBoost成功建立了预测模型，以最优特征子集实现了对COVID-19患者重症进展风险的早期预测。
Abstract
Objective
2
To construct an XGBoost prediction model to predict disease severity of COVID-19 based on clinical characteristics dataset of COVID-19 patients.
Methods
2
A total of 347 laboratory-confirmed COVID-19 patients with complete medical information admitted from Feb 10 to April 5
2020 were screened from the medical record system of Huoshenshan Hospital. Firstly
21 features with significant differences were screened out as input features for the training model. Bayesian optimization was performed on the constructed XGBoost model to adjust the parameters
and the optimal combination of features was filtered based on feature importance. To further analyze the positive and negative effects of the numerical size of each feature on the prediction results
each feature importance was quantified and attributed by using SHapley Additive exPlanations (SHAP). Finally
the performance of the XGBoost prediction model was evaluated
and the model was compared and discussed with other machine learning methods
including support vector machine (SVM)
naïve Bayes (NB)
logical regression (LR)
and k-nearest neighbors (KNN).
Results
2
In this study
21 features with significant differences between the severe and non-severe groups were selected for training and validation. The optimal subset with 10 features in the k-nearest neighbor model obtained the highest value of area under curve (AUC) among the 4 models in the validation set. XGBoost and support vector machine were better than other machine learning methods in terms of prediction performance (AUC: 0.942 0
and 0.959 4 on the test set
respectively)
and the training speed of XGBoost was significantly faster.
Conclusion
2
A prediction model based on XGBoost is successfully built to achieve early prediction of disease severity of COVID-19 patients.
关键词
Keywords
references
WHO. Coronavirus (COVID-19) dashboard[R/OL]. (2021-07-23)[2021-07-23]: https://covid19.who.int/.
BURKI T K. Lifting of COVID-19 restrictions in the UK and the Delta variant[J]. Lancet Respir Med, 2021, 9(8): e85. DOI: 10.1016/S2213-2600(21)00328-3.
CHEN N S, ZHOU M, DONG X, et al . EpidemioLogical and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study[J ] . Lancet, 2020, 395(10223): 507-513. DOI: 10.1016/S0140-6736(20)30211-7.
CHEN T, WU D, CHEN H, et al . Clinical characteristics of 113 deceased patients with coronavirus disease 2019: retrospective study[J ] . BMJ, 2020: m1295. DOI: 10.1136/bmj.m1091.
HUANG C L, WANG Y M, LI X W, et al . Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China[J ] . Lancet, 2020, 395(10223): 497-506. DOI: 10.1016/S0140-6736(20)30183-5.
GUAN W J, NI Z Y, HU Y, et al . Clinical characteristics of coronavirus disease 2019 in China[J ] . N Engl J Med, 2020, 382(18): 1708-1720. DOI: 10.1056/nejmoa2002032.
LI L Q, HUANG T, WANG Y Q, et al . COVID-19 patients' clinical characteristics, discharge rate, and fatality rate of meta-analysis[J ] . J Med Virol, 2020, 92(6): 577-583. DOI: 10.1002/jmv.25757.
ZHOU F, YU T, DU R H, et al . Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study[J ] . Lancet, 2020, 395(10229): 1054-1062. DOI: 10.1016/S0140-6736(20)30566-3.
XU F M, CHEN X, YIN X R, et al . Prediction of disease progression of COVID-19 based upon machine learning[J ] . Int J Gen Med, 2021, 14: 1589-1598. DOI: 10 .2147/IJGM.S294872.
WHO. Clinical management of severe acute respiratory infection when Novel coronavirus (nCoV) infection is suspected: interim guidance[S/OL]. (2020-03-13)[2021-10-27]: https://www.who.int/docs/default-source/coronaviruse/clinical-management-of-novel-cov.
JI D, ZHANG D, XU J, et al . Prediction for progression risk in patients with COVID-19 pneumonia: the CALL score[J ] . Clin Infect Dis, 2020, 71(6): 1393-1399. DOI: 10.1093/cid/ciaa414.
ZHOU Y L, ZHANG Z C, TIAN J, et al . Risk factors associated with disease progression in a cohort of patients infected with the 2019 novel coronavirus[J ] . Ann Palliat Med, 2020, 9(2): 428-436. DOI: 10.21037/apm.2020.03.26.
WU C M, CHEN X Y, CAI Y P, et al . Risk factors associated with acute respiratory distress syndrome and death in patients with coronavirus disease 2019 pneumonia in Wuhan, China[J ] . JAMA Intern Med, 2020, 180(7): 934. DOI: 10.1001/jamainternmed.2020.0994.
YE Z, SONG B. Liver injury in COVID-19: Diagnosis and associated factors[J]. Liver Int, 2020, 40(8): 2040-2041. DOI: 10.1111/liv.14501.
YIP T C F, LUI G C Y, WONG V W S, et al . Liver injury is independently associated with adverse clinical outcomes in patients with COVID-19[J ] . Gut, 2021, 70(4): 733-742. DOI: 10.1136/gutjnl-2020-321726.
ZHANG Y, ZHENG L, LIU L, et al . Liver impairment in COVID-19 patients: a retrospective analysis of 115 cases from a single centre in Wuhan city, China[J ] . Liver Int, 2020, 40(9): 2095-2103. DOI:10.1111/liv.14455.
0
浏览量
0
下载量
0
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
