Background: Mild cognitive impairment (MCI) is considered a s the early stage of Alzheimer's Disease (AD). The purpose of our study was to analyze the basic characteristics andserum and imaging biomarkers for the diagnosis of MCI patients as a more objective and accurate approach. Methods: The Montreal Cognitive Test was used to test 119 patients aged ≥65. Such serum bio-markers were detected as preprandial blood glucose, triglyceride, total cholesterol, Aβ1-40, Aβ1-42, and P-tau. All the subjects were scanned with 1.5T MRI (GE Healthcare, WI, USA) to obtain DWI, DTI, and ASL images. DTI was used to calculate the anisotropy fraction (FA), DWI was used to calculate the apparent diffusion coefficient (ADC), and ASL was used to calculate the cerebral blood flow (CBF). All the images were then registered to the SPACE of the Montreal Neurological Institute (MNI). In 116 brain regions, the medians of FA, ADC, and CBF were extracted by automatic anatomical labeling. The basic characteristics included gender, education level, and previous disease history of hypertension, diabetes, and coronary heart disease. The data were randomly divided into training sets and test ones. The recursive random forest algorithm was applied to the diagnosis of MCI patients, and the recursive feature elimination (RFE) method was used to screen the significant basic features and serum and imaging biomarkers. The overall accuracy, sensitivity, and specificity were calculated, respectively, and so were the ROC curve and the area under the curve (AUC) of the test set. Results: When the variable of the MCI diagnostic model was an imaging biomarker, the training accuracy of the random forest was 100%, the correct rate of the test was 86.23%, the sensitivity was 78.26%, and the specificity was 100%. When combining the basic characteristics, the serum and imaging biomarkers as variables of the MCI diagnostic model, the training accuracy of the random forest was found to be 100%; the test accuracy was 97.23%, the sensitivity was 94.44%, and the specificity was 100%. RFE analysis showed that age, Aβ1-40, and cerebellum_4_6 were the most important basic feature, serum biomarker, imaging biomarker, respectively. Conclusion: Imaging biomarkers can effectively diagnose MCI. The diagnostic capacity of the basic trait biomarkers or serum biomarkers for MCI is limited, but their combination with imaging biomarkers can improve the diagnostic capacity, as indicated by the sensitivity of 94.44% and the specificity of 100% in our model. As a machine learning method, a random forest can help diagnose MCI effectively while screening important influencing factors.

Few predictive studies have been reported on the efficacy of atorvastatin in reducing lipoprotein cholesterol to be qualified after 1-month course of treatment in different individuals. A total of 14,180 community-based residents aged ≥ 65 received health checkup, 1013 of whom had low-density lipoprotein (LDL) higher than 2.6mmol/L so that they were put on 1-month course of treatment with atorvastatin. At its completion, lipoprotein cholesterol was measured again. With < 2.6 mmol/L considered as the treatment standard, 411 individuals were judged as the qualified group, and 602, and as the unqualified group. The basic sociodemographic features covered 57 items. The data were randomly divided into train sets and test ones. The recursive random-forest algorithm was applied to predicting the patients response to atorvastatin, the recursive feature elimination method, to screening all the physical indicators. The overall accuracy, sensitivity and specificity were calculated, respectively, and so were the receiver operator characteristic curve and the area under the curve of the test set. In the prediction model on the efficacy of 1-month treatment of statins for LDL, the sensitivity, 86.86%; and the specificity, 94.83%. In the prediction model on the efficacy of the same treatment for triglyceride, the sensitivity, 71.21%; and the specificity, 73.46%. As to the prediction of total cholesterol, the sensitivity, 94.38%; and the specificity, 96.55%. And in the case of high-density lipoprotein (HDL), the sensitivity, 84.86%; and the specificity, 100%. recursive feature elimination analysis showed that total cholesterol was the most important feature of atorvastatin efficacy of reducing LDL; that HDL was the most important one of its efficacies of reducing triglycerides; that LDL was the most important one of its efficacies of reducing total cholesterol; and that triglyceride was the most important one of its efficacies of reducing HDL. Random-forest can help predict whether atorvastatin efficacy of reducing lipoprotein cholesterol to be qualified after 1-month course of treatment in different individuals.