基于可解释性机器学习的儿科护士付出-回报失衡风险预测模型的构建
打开文本图片集
Construction of the risk prediction model for pediatric nurses'effort-reward imbalance based on interpretable machine learning
CHEN Zhengju，ZHANG Xiumei， SHAO Peng
TheFirstAffiliatedHospitalofAnhuiMedicalUniversity，Anhui23oo22China *Corresponding Author SHAO Peng，E-mail：18756084137@163.com
AbstractObjective：Toconstructtheriskpredictionmodelforpediatricnursesefortrewardimbalancebasedointerpretablemachine leaming，andtocomparethepredictiveperformanceofdiferent models.Toexplaintheresultsoftheoptimalmodelusing SHAP interpretationMethods：Usingtheconveniencesamplingmethod，atotalof414pediatricursesfrom6hospitalsinAnhuiprovince， Shanxiprovince，JiangxiprovinceandHunanprovinceinJuneO25wereselectedastheresearchsubjects.Theywererandomlydiided into training set and validation set at a ratio of 7：3. The Chinese Nurse Stressor Scale and the Effort-Reward Imbalance Questionnaire scalewereusedforinvestigation.LASSOregresionwasemploedtosreenthecharacteristicvariablesndidentifytheiportant predictors.Theimportantpredictorswereincorporatedintothemachinelearingmodeltoconstructthreeriskpredictionmodels for pediatric nursesfortrdibaceLgisticgesionodel，ExtreeGadntoigodelndadomorstel areasunderthereceiveroperatingcharactersticcurves（AUC），accuracysensitiy，andF1scoreofthemodelswerecomparedto evaluatethepredictiveperformanceofthemodelsandselectheoptimalmodel.TheSHAPexplanationwasusedtointerprettheoptimal model.Results：LASOregresionidentifiedthreeimportantfactors：teumberofnightshiftsprmonthorkloadadtiellcation， andeducationalbackground.TheAUCvaluesofthethreepreditionmodelsLogisticregresiomodel，ExtremeGradientBoosting modeladel）eeelicisof4d 0.421，0.731，andO13，andFsoresofO.547O7，andO98.TeAPexplanatioresultssoedtattheimportanceraingof theinfluencingfactorswerethenumberofnightshiftspermonth，workloadandtimealocation，andeducationalbackground. Conclusions：Theriskpredictionmodelforpediatricursesefortrewardimbalancebasedoninterpretablemachinelearingcostructed byRandomForesthasbetterperformancethanLogisticregressionandExtremeGradientBoostingmodel.Personalizedpredictions shouldbemadebasedonthenumberofnightshiftseachnursetakespermonth，orkloadandtimealocationandeducationalackgroun. Itprovidesareferencefortheearlyidentificationoftheimbalancebetweenefortandrewardforthenursesandtheformulationof personalized intervention measures.
Keywordspediatric nurses;effortreward imbalance; machine learning;LASSOregressionanalysis; influencing factors
付出-回报失衡是指一种高付出低回报的工作状态，一般用于评估工作压力大小。（剩余10618字）