肺癌病人治疗期输液港医用粘胶相关皮肤 损伤风险预测模型的构建

打开文本图片集

AbstractObjective：Toaalyzetheriskfactorsformedicaladesiverelatedskinnjury（MARSI）ininfusionportsduringthetreatet periodofungcancerpatients.Andtoestablishariskpredictionmodel，soastoprovidereferenceforclinicalursingintervention. Methods：Artrospetiecolltionof6Optientsithimplantableestwallportshowerhospitalidinterespiratoryadcriical caremedicinedepartmentofatertiarygradeAgeneralhospitalfromJanuary2O23toApril2O24wasconducted.Logisticrgesion model，decisiotrifiioeesoCodelddfotoelsedtablshsdictioelsfor medicaladhesiverelatedskinijuryinifusionportsdringthetreatmentperiodoflungcancerpatients.Theacuracysiiity specificitysiiedictiluegatiepictielueKapfnt，nddeeatingctestic （ROC）curve（AUC）of the three models werecompared toevaluate theirperformance.Results：TheacuracyofLogisticregresion model，decision tree CART model，and random forest models were 84% 86% ，and 86% ，respectively.The specificity were 97% 98% ， and 97% .The sensitivitywere 54%，59% ，and 61% .The positive predictive valueswere 54% 59% ，and 61% .Thenegative predictive values were 97% ， 98% ，and 97% .The Kappa values were O.57，0.63，and 0.64.The AUC were 0.83，0.87，and O.86.There were statisticallysignificantintheAUCdiferencesamongLogisticregresionmodel，decisiontreeCARTmodel，andandomforest ⌈P<0.05⌉ Skin toxicitywasacommon predictorforthreemodels.Conclusions：ComparedwithLogisticregresionmodel，decisiontreeCART modelandrandomforestmodelhadbetterperformance inconstructingariskpredictionmodelforininfusionportsduringthetreatment periodoflungcancepatients，itouldprovideeferenceforcliicalursestopredictteriskofmedicaladesiveelatedkinijuryn infusion ports during the treatment period of lung cancer patients.

Keywordsinfusionport;medicaladhesiverelatedskinijuries;predictive model;Logisticregresson;decisiontree CAT；adom forest method

摘要目的：分析肺癌病人治疗期输液港发生医用粘胶相关皮肤损伤（medical adhesive related skin injury，MARSI）的危险因素，并建立风险预测模型，以期为临床护理干预提供参考。（剩余12845字）