Please wait a minute...
文章检索
预防医学  2021, Vol. 33 Issue (8): 762-767    DOI: 10.19485/j.cnki.issn2096-5087.2021.08.002
  论著 本期目录 | 过刊浏览 | 高级检索 |
两种急性百草枯中毒死亡预测模型比较
孙颖1,2, 张瑞3, 于海涛4, 邹晓艳2, 赵鹏5
1. 青岛大学基础医学院,山东 青岛 266075;
2. 青岛市第八人民医院消化内一科;
3. 山东省立医院药剂科;
4. 青岛市市立医院重症医学科;
5. 青岛大学附属医院病理科
Comparison of two prediction models for mortality ofacute paraquat poisoning
SUN Ying*, ZHANG Rui, YU Haitao, ZOU Xiaoyan, ZHAO Peng
*School of Basic Medicine, Qingdao University, Qingdao, Shandong 266075, China;
Department of Gastroenterology, Qingdao Eighth People's Hospital
全文: PDF(1071 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 目的 比较Cox比例风险回归模型和极端梯度上升(XGBoost)模型对急性百草枯中毒(APP)死亡的预测效果。方法 选择青岛市第八人民医院和山东省立医院于2018年1月1日―2020年12月1日收治的APP患者为研究对象,采用随机数表法分为训练组和验证组。分别建立Cox比例风险回归模型和XGBoost模型筛选APP患者死亡的预测因素。采用受试者工作特征曲线(ROC)分析两种模型的预测效能,采用Hosmer-Lemeshow检验评价两种模型的校准度。结果 共纳入APP患者150例,训练组和验证组各75例,分别死亡52例和55例,占69.33%和73.33%。Cox比例风险回归模型结果显示,摄入百草枯剂量、服毒至就诊时间、首次灌流时间、首次呕吐时间、谷草转氨酶、谷丙转氨酶、血肌酐、尿素氮、白细胞、动脉血乳酸、肌酸激酶同工酶、血糖、血钙和血钾是APP患者死亡的独立预测因素(均P<0.05)。XGBoost模型结果显示,预测能力由强到弱的因素依次为服毒至就诊时间、首次呕吐时间、首次灌流时间、动脉血乳酸、白细胞、摄入百草枯剂量、血肌酐、血钾、血钙、肌酸激酶同工酶、血糖、谷草转氨酶、尿素氮和谷丙转氨酶。XGBoost模型预测APP患者死亡的AUC值为0.972,大于Cox比例风险回归模型的0.921(P<0.05)。Cox比例风险回归模型、XGBoost模型的预测结果与实际死亡情况的一致性均较好(P>0.05)。结论 Cox比例风险回归模型和XGBoost模型筛选APP患者死亡的预测因素一致,但后者预测能力优于前者。关键词:急性百草枯中毒;Cox比例风险回归模型;极端梯度上升模型;预测
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
孙颖
张瑞
于海涛
邹晓艳
赵鹏
关键词 acute paraquat poisoningCox proportional hazard regression modelextreme gradient boosting modelprediction    
AbstractObjective To compare the effects of Cox proportional hazard regression model (Cox model) and extreme gradient boosting model ( XGBoost model ) on the prediction of the mortality of acute paraquat poisoning (APP). Methods The APP cases admitted to Qingdao Eighth People's Hospital and Shandong Provincial Hospital from January 1st of 2018 to December 1st of 2020 was recruited and divided into a training group and a verification group by a random number table. The Cox model and XGBoost model were established to select the predictors for APP mortality. Receiver operating characteristic ( ROC ) curve was drawn to analyze the predictive power of the two models, and the calibration was evaluated using Hosmer-Lemeshow test. Results Totally 150 APP cases were recruited. There were 75 cases each in the training group and in the verification group, with 52 and 55 cases died respectively, accounting for 69.33% and 73.33%. The Cox model showed that paraquat intake, the time from taking poison to seeing a doctor, the time for the first perfusion, the time for the first vomiting, aspartate aminotransferase, alanine aminotransferase, serum creatinine, blood urea nitrogen, white blood cell, lactic acid, creatine kinase isoenzymes, glucose, serum calcium and serum potassium were the predictors of APP mortality ( all P<0.05 ). The XGboost model showed that the predictive power of the factors in a descending order were the time from taking poison to seeing a doctor, the time for the first vomiting, the time for the first perfusion, lactic acid, white blood cell, paraquat intake, serum creatinine, serum potassium, serum calcium, creatine kinase isoenzymes, glucose, aspartate aminotransferase, blood urea nitrogen and alanine aminotransferase. The area under curve ( AUC ) of the XGBoost model for predicting was 0.972, which was greater than 0.921 of the Cox model ( P<0.05 ). The predicted results of the Cox model and XGBoost model were consistent with the actual situation ( P>0.05 ). Conclusion The Cox model and XGBoost model are consistent in predicting the mortality of APP, but the latter is better.
Key wordsacute paraquat poisoning    Cox proportional hazard regression model    extreme gradient boosting model    prediction
收稿日期: 2021-01-26      出版日期: 2021-08-10
ZTFLH:  R446.1  
基金资助:山东省自然科学基金(ZR2018PH037)
通信作者: 赵鹏,E-mail:saxmd41@163.com   
作者简介: 孙颖,本科,副主任医师,主要从事消化内科工作
引用本文:   
孙颖, 张瑞, 于海涛, 邹晓艳, 赵鹏. 两种急性百草枯中毒死亡预测模型比较[J]. 预防医学, 2021, 33(8): 762-767.
SUN Ying, ZHANG Rui, YU Haitao, ZOU Xiaoyan, ZHAO Peng. Comparison of two prediction models for mortality ofacute paraquat poisoning. Preventive Medicine, 2021, 33(8): 762-767.
链接本文:  
http://www.zjyfyxzz.com/CN/10.19485/j.cnki.issn2096-5087.2021.08.002      或      http://www.zjyfyxzz.com/CN/Y2021/V33/I8/762
[1] XIAO Q,WANG W,QI H,et al.Continuous hemopermfusion relieves pulmonary fibrosis in patients with acute mild and moderate paraquat poisoning[J].J Toxicol Sci,2020,45(10):611-617.
[2] WEN C C,LIN F Y,HUANG B G,et al.Metabolomics analysis in acute paraquat poisoning patients based on UPLC-Q-TOF-MS and machine learning approach[J].Chem Res Toxicol,2019,32(4):629-637.
[3] 姚婷婷,刘媛媛,李长平,等.生存资料回归模型分析——生存资料Cox比例风险回归模型分析[J].四川精神卫生,2020,33(1):27-32.
[4] GUAN X,ZHANG B,FU M,et al.Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study[J].Ann Med,2021,53(1):257-266.
[5] CHRISTOPHER T,BRODY J P.Evaluation of a genetic risk score for severity of COVID-19 using human chromosomal-scale length variation[J/OL].Hum Genomics,2020,14(1)[2021-06-04].https://pubmed.ncbi.nlm.nih.gov/33036646/.DOI: 10.1186/s40246-020-00288-y.
[6] SEGAL Z,KALIFA D,RADINSKY K,et al.Machine learning algorithm for early detection of end-stage renal disease[J]. BMC Nephrol,2020,21(1):518-527.
[7] 蔺轲,林瑜,孔桂兰.基于XGBoost算法的ICU脓毒症患者住院死亡风险预测研究[J].中国卫生信息管理杂志,2018,15(5):536-540,563.
[8] 中国医师协会急诊医师分会.急性百草枯中毒诊治专家共识(2013)[J].中国急救医学,2013,33(6):484-489.
[9] DELONG E R,DELONG D M,CLARKE-PEARSON D L.Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach[J].Biometrics,1988,44(3):837-845.
[10] SHILEI L,DANNA Z,YONG L,et al.Arterial lactate in predicting mortality after paraquat poisoning: a meta-analysis[J/OL].Medicine (Baltimore),2018,97(34)[2021-06-04].https://pubmed.ncbi.nlm.nih.gov/30142762/.DOI: 10.1097/MD.00000000
00011751.
[11] 颜梅,胡乔华,莫李婵,等.急性百草枯农药中毒患者35例预后相关因素分析[J].岭南急诊医学杂志,2020,25(2):149-150.
[12] FENG S Y,GAO J, LI Y.A retrospective analysis of leucocyte count as a strong predictor of survival for patients with acute paraquat poisoning[J/OL].PLoS One,2018,13(7)[2021-06-04].https://pubmed.ncbi.nlm.nih.gov/30044873/.DOI: 10.1371/journal.pone.0201200.
[13] 马涛,邢宏运,李晓明,等.急性百草枯中毒的预后因素分析[J].医药导报,2020,39(6):849-850.
[14] FENG M X,LI Y N,RUAN W S,et al.Predictive value of the maximum serum creatinine value and growth rate in acute paraquat poisoning patients[J/OL].Sci Rep,2018,8(1)[2021-06-04].https://pubmed.ncbi.nlm.nih.gov/30072769/.DOI: 10.1038/s41598-018-29800-0.
[15] 牛丽丹,张建新,郝同琴,等.入院时血浆百草枯浓度及百草枯中毒严重指数评估患者中毒程度及预后的价值比较[J].实用医院临床杂志,2018,15(3):87-88.
[16] 王鸾,蔡雪,赵敏.急性百草枯中毒死亡危险因素分析[J].中国医科大学学报,2018,47(3):237-239,243.
[17] 武小娟,李彦国,孟舰,等.早期血糖和离子水平对急性百草枯中毒患者的预后评估[J].现代预防医学,2018, 45(1):115-118.
[18] 田飞,张蓉,郭庆,等.急性百草枯中毒预后影响因素的研究[J].巴蜀医学,2020,3(1):19-25,38.
[19] 袁晓春,李金奎,陈中伟,等.Cox比例风险回归模型分析急性百草枯中毒者预后影响因素[J].宁夏医科大学学报,2018, 233(2):68-70.
[20] 杨志燕,黄天宝,王树山,等.基于支持向量机的急性百草枯中毒预后模型的建立与评价[J].南京医科大学学报,2018,38(10):1467-1471.
[1] 骆文龙, 胡婷, 包文星. 直接静脉采血、留置针采血和末梢采血的血常规检测结果比较[J]. 预防医学, 2017, 29(11): 1187-1188.
[2] 郑会琴,罗海霞,陈晓刚. 孕妇妊娠早期和中期血细胞参数分析[J]. 预防医学, 2017, 29(12): 1271-1272.
[3] 王海蓉, 符文杰, 陈垒. 湿法消化-原子荧光光谱法测尿中砷[J]. 预防医学, 2017, 28(3): 323-324.
[4] 王海蓉, 符文杰, 陈垒. 湿法消化-原子荧光光谱法测尿中砷[J]. 预防医学, 2016, 28(3): 323-324.
[5] 应英, 王立媛, 虞晓珍, 张念华, 赵永信, 朱心强. 电感耦合等离子体质谱法和石墨炉原子吸收光谱法测定冻干血铬比较[J]. 预防医学, 2019, 31(7): 751-753.
[6] 关婷, 杨雪莹, 张东梅, 杨娟, 张宏光, 焦楷磊, 马旭, 赵君. 育龄女性孕前促甲状腺激素与空腹血糖水平的关联性研究[J]. 预防医学, 2020, 32(6): 631-635.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed