基于随机森林算法的早产儿PICC导管继发性异位风险预测模型的构建与验证

打开文本图片集

AbstractObjective：Toinvestigatethekeyriskfactorsforsecondaryectopicsofcatheteraftercentralvenouscatheterinsertion（PICC） throughperipheralveins，ndtoconstructandvalidateariskpredictionmodelbasedontherandomforestalgorithm.Methods：Thedata of590preterminfants hospitalizedinthedepartmentofneonatologyofatertiaryspecialtyhospitalinShanxiprovincewithPICC catheterization were retrospectively collected，and the data were randomly divided into training set（ n=413 ）and validation set（n=177） in a ratio of 7：3. Eighteen clinical indicators were selected as predictors for whether secondary ectopic of the catheter occurred at the tip afterPICCcatheterzationinpreteifantsBasedontherndomforestagorith，ariskpredictionmodelforsecodaryectopicectopic ofPICCcatheters inpreteintsascostructed，themporaeofrisfctrsasaked，ndaAPplotasplotedpan thecontributionofeachvariabletothepredictionofmodeloutput.Theconfusion matrixanalysisofthemodel wascariedoutusing the validationsetdata，andthepredictionefectofthemodelwasevaluatedbyusingtheaccuracy，sensitivity，specificityandreceiver operatingcharacteristcROC）curves.Results：TheincidenceofsecondaryectopicofPCCcatheterin413preterminfants inthetraining set was 39.0% ，andthe keyfactors screenedbytherandom forestalgorithm werethefirstX-raylocalizationresult，secondarycatheter fixation，mehaicalntiltionndeightgiateespectiely.Itevdationst，tecuracyofteiskpedictiooelwas 81.92% ，the sensitivity was 71.21% ，the specificity was 88.29% ，the positive predictive value was 78.33% ，the negative predictive value was 83.76% ，and the AUC value was 0.870（95%CI：0.817-0.923 ）.Conclusions：The risk prediction model constructed based on the randomforestalgorithmdemonstratesgoodpredictiveperformance.Itcouldpotentiallprovideasientifcbasisforthesafeandffcent clinical use of PICC in premature infants.

Keywordspremature infants;PICC;secondary ectopia; random forest algorithm; risk prediction model

早产儿各器官、系统发育尚未成熟，无法依靠自身从外界获得足够营养，缺乏维持生命的物质基础，常需依赖持续静脉营养和药物治疗以维持其生长发育需求[1。（剩余8319字）