中华急诊医学杂志
中華急診醫學雜誌
중화급진의학잡지
CHINESE JOURNAL OF EMERGENCY MEDICINE
2014年
3期
308-313
,共6页
孙明伟%江华%蔡斌%彭谨%杨浩%周志远%陈伟%Charles Damien Lu%曾俊
孫明偉%江華%蔡斌%彭謹%楊浩%週誌遠%陳偉%Charles Damien Lu%曾俊
손명위%강화%채빈%팽근%양호%주지원%진위%Charles Damien Lu%증준
地震伤%创伤%病死率%大数据%多器官功能损害%模式识别%偏最小二乘法分类判别%数据挖掘%病例对照
地震傷%創傷%病死率%大數據%多器官功能損害%模式識彆%偏最小二乘法分類判彆%數據挖掘%病例對照
지진상%창상%병사솔%대수거%다기관공능손해%모식식별%편최소이승법분류판별%수거알굴%병례대조
Earthquake injury%Trauma%Mortality%Big data%Multiple organ dysfunctional syndrome%Pattern recognition technique%Partial least squares discriminant analysis%Data mining%Case-control
目的 模式识别技术(PRT)是一种挖掘重要信息的新型工具,可以从海量数据中提取新的知识.基于汶川特大地震中创伤患者的数据,笔者采用PRT建立地震伤员结局预测模型,旨在为提高灾难医学救援水平提供一种新的方法.方法 采用回顾性数据挖掘方法,数据来自于四川省医学科学院创伤数据中心2008年5月12日至20日收治的2316例住院地震伤患者病例信息.将患者资料按照生存与死亡、是否发生多器官功能不全综合征(multiple organ dysfunction syndrome,MODS)分组.根据正态性分布检验结果,计量资料以均数±标准差(-x±s)或者中位数(四分位数)表示,统计检验采用Student T检验或者Wilcox检验;计数资料采用构成比表示,统计检验采用x2检验或者Fishcr检验.多元统计分析采用偏最小二乘法判别分析(partial least squarediscriminant analysis,PLS-DA).多元聚类图采用二维主成分的PLS的投影图,并采用重要性投影指标值(variable important projection,VIP)筛选与临床结局相关的重要变量,工效曲线(receiveroperating characteristic curve,ROC)作变量灵敏性分析.结果 经数据清理后1919例患者的病例资料纳入研究;筛选出31项人口学指标、生理-生化指标以及干预因素作为暴露参数;获得36例院内死亡病例和17例MODS病例.MODS相关病死率为47.1％.经过PLS-DA分析,二维主成分得分图可以辨识出生存、MODS和死亡模式.对病死率和MODS进行预测,ROC曲线下面积(area under curve,AUC)分别为0.882和0.979.PLS-DA的重要性投影指标值(VIP)确定了8项生理指标(pH,BE,PaCO2,PaO2,HCO3-1,SBHCO3,Cr和首日补液量)构成了与院内死亡和MODS发生的相关模型.结论 研究建立了一项可以预测特大地震创伤入院患者预后模型(由入院接受创伤治疗的生理-生化指标集合和液体复苏干预构成).基于该模型,将有助于开发帮助医务人员在特大灾难医学救援中早期预判高危患者的计算机辅助诊断系统.
目的 模式識彆技術(PRT)是一種挖掘重要信息的新型工具,可以從海量數據中提取新的知識.基于汶川特大地震中創傷患者的數據,筆者採用PRT建立地震傷員結跼預測模型,旨在為提高災難醫學救援水平提供一種新的方法.方法 採用迴顧性數據挖掘方法,數據來自于四川省醫學科學院創傷數據中心2008年5月12日至20日收治的2316例住院地震傷患者病例信息.將患者資料按照生存與死亡、是否髮生多器官功能不全綜閤徵(multiple organ dysfunction syndrome,MODS)分組.根據正態性分佈檢驗結果,計量資料以均數±標準差(-x±s)或者中位數(四分位數)錶示,統計檢驗採用Student T檢驗或者Wilcox檢驗;計數資料採用構成比錶示,統計檢驗採用x2檢驗或者Fishcr檢驗.多元統計分析採用偏最小二乘法判彆分析(partial least squarediscriminant analysis,PLS-DA).多元聚類圖採用二維主成分的PLS的投影圖,併採用重要性投影指標值(variable important projection,VIP)篩選與臨床結跼相關的重要變量,工效麯線(receiveroperating characteristic curve,ROC)作變量靈敏性分析.結果 經數據清理後1919例患者的病例資料納入研究;篩選齣31項人口學指標、生理-生化指標以及榦預因素作為暴露參數;穫得36例院內死亡病例和17例MODS病例.MODS相關病死率為47.1％.經過PLS-DA分析,二維主成分得分圖可以辨識齣生存、MODS和死亡模式.對病死率和MODS進行預測,ROC麯線下麵積(area under curve,AUC)分彆為0.882和0.979.PLS-DA的重要性投影指標值(VIP)確定瞭8項生理指標(pH,BE,PaCO2,PaO2,HCO3-1,SBHCO3,Cr和首日補液量)構成瞭與院內死亡和MODS髮生的相關模型.結論 研究建立瞭一項可以預測特大地震創傷入院患者預後模型(由入院接受創傷治療的生理-生化指標集閤和液體複囌榦預構成).基于該模型,將有助于開髮幫助醫務人員在特大災難醫學救援中早期預判高危患者的計算機輔助診斷繫統.
목적 모식식별기술(PRT)시일충알굴중요신식적신형공구,가이종해량수거중제취신적지식.기우문천특대지진중창상환자적수거,필자채용PRT건입지진상원결국예측모형,지재위제고재난의학구원수평제공일충신적방법.방법 채용회고성수거알굴방법,수거래자우사천성의학과학원창상수거중심2008년5월12일지20일수치적2316례주원지진상환자병례신식.장환자자료안조생존여사망、시부발생다기관공능불전종합정(multiple organ dysfunction syndrome,MODS)분조.근거정태성분포검험결과,계량자료이균수±표준차(-x±s)혹자중위수(사분위수)표시,통계검험채용Student T검험혹자Wilcox검험;계수자료채용구성비표시,통계검험채용x2검험혹자Fishcr검험.다원통계분석채용편최소이승법판별분석(partial least squarediscriminant analysis,PLS-DA).다원취류도채용이유주성분적PLS적투영도,병채용중요성투영지표치(variable important projection,VIP)사선여림상결국상관적중요변량,공효곡선(receiveroperating characteristic curve,ROC)작변량령민성분석.결과 경수거청리후1919례환자적병례자료납입연구;사선출31항인구학지표、생리-생화지표이급간예인소작위폭로삼수;획득36례원내사망병례화17례MODS병례.MODS상관병사솔위47.1％.경과PLS-DA분석,이유주성분득분도가이변식출생존、MODS화사망모식.대병사솔화MODS진행예측,ROC곡선하면적(area under curve,AUC)분별위0.882화0.979.PLS-DA적중요성투영지표치(VIP)학정료8항생리지표(pH,BE,PaCO2,PaO2,HCO3-1,SBHCO3,Cr화수일보액량)구성료여원내사망화MODS발생적상관모형.결론 연구건립료일항가이예측특대지진창상입원환자예후모형(유입원접수창상치료적생리-생화지표집합화액체복소간예구성).기우해모형,장유조우개발방조의무인원재특대재난의학구원중조기예판고위환자적계산궤보조진단계통.
Objective Massive earthquake is one of disasters resulting in huge numbers of heavy and serious casualties.Identifying risk factors that lead to organ failure and death is crucial for improving trauma service performance.Pattern recognition technique (PRT) is a new tool for mining important information and in turn can generate new knowledge from huge amount of data.Here we use PRT to identify patterns in the cause of deaths of trauma patients from a massive earthquake in the Wenchuan,China.Methods We conducted a retrospectively data mining study.The data used is from a total of 2,316 casualties ambulated to the Sichuan Academy of Medical Sciences (SAMS) Trauma Service from May 12 to 20,2008 after a massive earthquake.Before analysis,data preprocessing and cleansing were conducted.We categorized patient data by survival/non-survival and MODS/non-MODS.According to the result of distribution test,quantitative data was described by mean ± standard deviation (SD) or median (quartile),Student t testing or Wilcox testing was employed.Qualitative data was described by ratio,x2 testing of fisher testing was employed.After mortality and multiple organ dysfunctional syndromes (MODS) related variables are acquired,partial least squares discriminant analysis (PLS-DA) algorithm was used to establish mortality and MODS correlation model.We adopted two principle components to establish PLS projection plotting,and used variable important projection (VIP) to screen variables that correlated with clinical outcome.Receiver operating characters (ROC) curve was used for sensitivity and specificity analysis.Results The records of 1919 patients were selected by data cleansing,and 31 demographical,physiological-biological parameters and intervention factors were acquired as exposure variables.There were 36 in-hospital death cases,and 17 MODS cases.MODS related mortality was 47.1％ (8/17).In PLS-DA,the first two principal components in the scatter plot could distinguish survival,MODS and deceased patients.For predicting mortality and MODS,the AUC of ROC was 0.882 and 0.979,respectively.VIP indicator (variable importance for the projection) of PLS-DA identified 8 physiological variables (pH,BE,PaCO2,PaO2,HCO3-1,SBHCO3,Cr,volume of fluid resuscitation at the first day in-hospital) comprised a pattern related to in-hospital death event and MODS.Conclusions This study shows that a significant pattern (comprised by a set of physiological-biological and fluid resuscitation intervention when patient reach to trauma service) emerges which can predict survival probability for hospitalized casualties injured during a massive earthquake.Application of this model may provide a tool to help disaster health providers identify most-at-risk patients,especially after a massive disaster when limited medical resources have to cope with huge numbers of victims.
