自发性脑出血病人抢救性气管插管风险预测模型的构建与验证

打开文本图片集

AbstractObjective：Toanalyzetheriskfactorsofemergencyendotrachealintubationinpatientswithspontaneousintracerebral hemorhage，ndtoconstructaiskpredictionmodel，andvrifyitMethods：Atotalof89patientswithspontaneousitracerebal hemorrageodmiedtoteemergencydepartentinatertiarygdeAospitalfroptember18tuary3，wee selectedasubjects.Acodingtothechronologicaloder，theyweredividedntoamodelinggroup（290cases）andavalidationgroup（99 cases）.TheLASSOregresionwasusedtoscreentheinfluencingfactorsofemergencyendotrachealintubationinpatientswith spontaneous intracerebralhemorrageAndtheLogisticriskpredictionmodelwasconstructed.Theareaunderthereceiveroperating characteristiccurve（ROC），calibrationcurve，Hosmer-Lemeshowtest，anddecisioncurve（DCA）wasusedtoverifythemodel.Results： Emergency endotracheal intubation occurred in 54 patients （18.6% ）with spontaneous intracerebral hemorrhage in modeling group. MultivariateLgistcegialissultsodtattgaustedaomobididC）igsel time，hearrate，xygesaturatin，odiiedEarlyWaigScaleMEWS）iameteroftelftpupil，ghtrflexoftelftpil，d lightreflexofthtpupileeteifluencingfctorsfomergecyndotachalnubatioipatietswitsontaneousitracebal hemorrhage.The area under the ROC curve in the modeling group was 0.906（95%CI 0.867-0.946） .The optimal cut-off value of the model prediction was O.l22，witha sensitivityof 94.4% ，aspecificityof 74.6% .TheYoudenindexwasO.69o.Hosmer-Lemeshowtest results showed that χ2=8.91 P=0.350 .The calibration curve had a high degree of coincidence with the reference line.The clinical decisioncurveindicatedthatthemodelhadgoodclinicaldecision-makingperformance.Conclusions：Theriskpredictionmodel constructedinthisstudycouldbettepredicttheoccurenceofemergencyendotrachealintubationinpatientswithspontaneous intracerebralhemorhage，providingreferenceforclinicalmedicalstafftoidentifythehigh-riskpopulationrequiringemergncy endotracheal intubation as earlyas possibleand formulate targeted interventions.

Keywords spontaneous intracerebral hemorhage；emergency endotracheal intubation；influencing factors；predictionmodels; LASSO regression

摘要目的：分析自发性脑出血病人抢救性气管插管的危险因素，构建风险预测模型，并对其进行验证。（剩余12645字）