ABSTRACT
Objective To collect the demographic,lifestyle and clinical factors of patients with cerebrovascular disease,and analyze the vascular cognitive impairment(VCI) factors and set up high-risk factors model.methods 505 patients with cerebrovascular disease hospitalization in department of geriatrics and neurology in hospital from October 2014 to October 2016 were enrolled.According to the questionaire survey data of demographics,lifestyle and clinical factors,the patients were divided into training set (421 cases) and test set (84 cases),and training set were divided into the non-VCI set (225 cases) and VCI set (196 cases).Analyzed the influence factors of VCI in patients with cerebrovascular disease by decision tree algorithm,and compared it with the Logistic regression analysis and chi-square and established the decision tree model for risk factors of VCI.Result sAccording to the VCI decision tree model,cross validation model recognition accuracy was 73.63%,while test set prediction accuracy was 73.81%.Alcoholism,hobbies,education level,tea drinking,diabetes,hypertension,diet,age,sleep and physical exercise were classification of node variables,while drinking was the root.The probability of VCI had significant difference (P<0.05) in the crowds with different risk factors.According to Result s of Logistic regression analysis,education level,drinking,exercise and diabetes were independent risk factors for VCI,while the model prediction accuracy was 66.98%,and test set prediction accuracy was 53.57%.According to the ROC curve of the decision tree model and the Logistic regression model,the decision tree model AUC was 0.737 (95%CI 0.688 to 0.786),and the Logistic regression model AUC was 0.664 (95%CI 0.612 to 0.717).Conclusion It is suggested that the decision tree model might be superior to logistic regression model in the prediction accuracy for VCI of patients with cerebrovascular disease.The alcoholism,diabetes,high blood pressure,high fat diet and insomnia are risk factors of VCI,while hobbies,high level of education,physical exercise and drinking tea can be the protective factors of the VCI.
ABSTRACT
Objective To investigate the impairment and the effect factors of encoding of episodic memory in patients with cerebral infarction. Methods 112 cases cerebral infarction patients and 115 healthy elders as controls were tested for episodic memory encoding with episodic pictures accomplished in computer, and compare the differences of encoding of episodic memory between the two groups. Results The remember indexes ( REM )of encoding memory test in patient group was significantly lower than that in control group( (70.81 ± 6.08 )vs (84.67 ± 4.49), P ＜ 0.01 ). The REM in patients with different impaired areas was significantly different ( (65.88 ± 5.73 ), (68.92 ± 4.65 ), (73.39 ± 6.20), ( 73.53 ± 3.44), P ＜ 0. 01 ). The REM in frontal lobe infarction group was significantly lower than that in temporal lobe infarction group (P ＜ 0.05 ), and in temporal lobe infarction group was significantly lower than that in basal ganglia infarction group and corona radiate infarction group (P＜0.05, P＜0. 01). The REM in cortex infarction group was significantly lower than that in under cortex group ( ( 67.37 ± 5.40 ), ( 73.46 ± 4.99 ), P ＜ 0.01 ). The REM in small cerebral infarction group was significantly higher than that in large cerebral infarction group( (72.67 ±4.47 ), (67.56 ± 6.18 ), P＜0.01 ). The size of cerebral infarction diameter was related with the REM( r= -0.39, P＜0. 01 ). The REM among control group,infarction with atrophy group, and infarction without atrophy group were significantly different( (67.03 ± 6. 17 ),( 72.84 ± 5. 00 ), ( 84.67 ± 4.49 ), P ＜ 0. 01 ). The REM in infarction with atrophy group was significantly lower than that in infarction without atrophy group and control group( both P＜0.01 ) ,The REM in infarction without atrophy group was significantly lower than that in control group (P ＜ 0.01). Conclusion The encoding of episodic memory was impaired in cerebral infarction patients. The infarction parts,size of infarction area and atrophy was related with the impairment of encoding of episodic memory.