Objective The adaptive synthetic sampling(ADASYN)algorithm and category inverse proportion weighting method weighting method were used to balance the datasets,then multi-classification prediction of cognitive normal(CN),mild cognitive impairment(MCI),and Alzheimer's disease(AD)combined with classifiers were performed.Methods Data were obtained from the Alzheimer's Disease Neuroimaging Initiative(ADNI)database,which was filled in missing values by random forest(RF),and feature subsets were selected by elastic net(EN).We chose ADASYN algorithm and category inverse proportion weighting method processing the category imbalance data,and four models were constructed by combining RF and support vector machine(SVM)respectively:ADASYN-RF,ADASYN-SVM,weighted random forest(WRF),and weighted support vector machine(WSVM).We evaluated the classification performance by macro-P,macro-R,macro-F1,ACC,Kappa value and area under the receiver operating characteristics curve(AUC).Results ADASYN-RF had the best classification performance(Kappa=0.938,AUC=0.980),followed by ADASYN-SVM.The most important classification features obtained using ADASYN-RF were CDRSB,LDELTOTAL,and MMSE,which have been clinically validated.Conclusions Both the ADASYN algorithm and the category inverse proportion weighting method can assist in improving classifier performance,and the ADASYN algorithm is superior.

Objective:To investigate the impact of residual cholesterol (RC) on the progression of arteriosclerosis in individuals receiving physical examination.Methods:A cross-sectional study. Participants aged 18 years and above who underwent arteriosclerosis testing at the Health Management Center of Zigong Fourth People′s Hospital from January to December 2023 were selected as the subjects of the study. A total of 9 016 subjects were included in this study, of whom 6 213 were considered to have arteriosclerosis. The physical examination conclusions, basic information (age, gender, body mass index, waist circumference, blood pressure, history of hypertension, history of smoking and drinking), and biochemical indicators (lipids, fasting blood glucose, liver and kidney function) were extracted in those individuals. Based on the examination results, the subjects were categorized into arteriosclerosis and normal groups. The RC levels of the participants were calculated using a formula and then the subjects were categorized into binary and quartile RC groups. Additionally, four regression models were used to analyze the impact of RC levels on the progression of arteriosclerosis while adjusting for various confounding factors.Results:The RC level was (0.63±0.44) mmol/L in the normal group and (0.76±0.61) mmol/L in the arteriosclerosis group. Based on level of RC, the normal group was divided into two subgroups: 652 individuals with elevated RC level and 2 241 with normal RC level. In the arteriosclerosis group, there were 2 069 individuals with elevated RC level and 4 144 with normal RC level. Grouped according to quartiles of RC level, the number of individuals with RC in the Q1-Q4 interval in the normal group was 838 (28.97%), 752 (25.99%), 760 (26.27%), and 543 (18.77%), respectively, showing a gradual decreasing trend. The number of individuals with RC in the Q1-Q4 interval in the arteriosclerosis group was 1 414 (22.76%), 1 438 (23.15%), 1 589 (25.58%), and 1 771 (28.51%), respectively, showing a gradual increasing trend. The difference between the groups was statistically significant ( P<0.05). After adjusting for various factors by four regression models, it was found that elevated RC levels increased the risk of arteriosclerosis progression, with a odds ratio ( OR) of 1.381, 1.242, 1.233, and 1.214, respectively. Additionally, individuals in the Q4 RC level quartile had 1.502, 1.318, 1.311, and 1.284-times higher risk of arteriosclerosis progression when compared to those in the Q1 quartile. Conclusion:The impact of RC on the progression of arteriosclerosis tend to stabilize and remain consistent, indicating that elevated RC is an independent risk factor for the progression of arteriosclerosis.