|
|
|
| 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 |
|
|
|
|
Abstract Objective 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.
|
|
Received: 26 January 2021
Revised: 04 June 2021
Published: 10 August 2021
|
|
|
|
|
|
[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. |
|
|
|
