Study On The Influencing Factors Of Mild Cognitive Impairment In Patients With End-stage Renal Disease

Background:Cognitive impairment has a high incidence in patients with end-stage renal disease,and it has a great impact on the therapeutic effect and quality of life of patients with end-stage renal disease.Mild cognitive impairment is reversible,so it is very important to screen the mild cognitive impairment in patients with end-stage renal disease early,and take effective prevention according to influencing factors.Many scholars have discussed the influencing factors of mild cognitive impairment in patients with end-stage renal disease,but the results are not clear.It is necessary to combine different data analysis methods to scientifically and deeply explore the influencing factors of mild cognitive impairment in patients with end-stage renal disease and to provide scientific basis for medical staff to evaluate the risk of mild cognitive impairment in patients with end-stage renal disease.Objective:To evaluate the cognitive function of patients with end-stage renal disease.To analyze the influencing factors of mild cognitive impairment based on Logistic regression and decision tree.To construct their models and evaluate and compare the overall effectiveness of the two models.Methods:This study was a descriptive study.Patients were selected from Peking Union Medical College Hospital,Beijing Chaoyang Hospital and Chinese people’s Liberation Army General Hospital,who were diagnosed with end-stage renal disease and underwent hemodialysis and peritoneal dialysis.The overall cognitive function of the subjects was evaluated,and the general data,physiological and psychological status,laboratory indicators and other information of patients with end-stage renal disease were collected.SPSS25.0 software was used for statistical description and statistical analysis.Based on multivariate Logistic regression analysis and CHAID algorithm of decision tree,the influencing factors of mild cognitive impairment in patients with end-stage renal disease were analyzed.Then their models were constructed and the area under the ROC curve,the sensitivity and specificity of the two models was evaluated and compared.Results:(1)A total of 337 patients with end-stage renal disease were included,and the incidence of mild cognitive impairment was 44.2%.The scoring rates of each field of cognitive function from high to low are orientation(97.7%),naming ability(93.0%),attention(93.0%),language ability(89.7%),visual space and executive function(75.0%),delayed recall ability(66.0%)and abstract ability(63.0%).(2)The results of multivariate Logistic regression analysis showed that age(P<0.001),time of education(P=0.004),diabetes(P=0.015)and history of cerebrovascular disease(P<0.001)might be related to mild cognitive impairment in patients with end-stage renal diseasc.The area under the ROC curve of Logistic model is 0.825,the sensitivity is 71.8%,and the specificity is 81.9%.(3)The decision tree model generates 20 nodes and 12 decision paths.A total of 6 variables entered the model,from top to bottom were age,history of cerebrovascular disease,diabetes,time of education,mode of dialysis and creatinine.The area under the ROC curve of the model is 0.833,the sensitivity of the model is 86.6%,and the specificity is 65.4%.Conclusion:The incidence of mild cognitive impairment is high in patients with end-stage renal disease.The combination of decision tree model and traditional Logistic model can scientifically and fully explore the influencing factors of mild cognitive impairment in patients with end-stage renal disease.The influencing factors are related to the general condition of patients,complicated disease,treatment methods and examination indicators,which should be paid attention to in clinic.