Developing effective risk prediction models is a cost-effective approach to predicting complications of chronic kidney disease (CKD) and mortality rates; however, there is inadequate evidence to support screening for CKD. In this study, four data mining algorithms, including a classification and regression tree, a C4.5 decision tree, a linear discriminant analysis, and an extreme learning machine, are used to predict early CKD. The study includes datasets from 19,270 patients, provided by an adult health examination program from 32 chain clinics and three special physical examination centers, between 2015 and 2019. There were 11 independent variables, and the glomerular filtration rate (GFR) was used as the predictive variable. The C4.5 decision tree algorithm outperformed the three comparison models for predicting early CKD based on accuracy, sensitivity, specificity, and area under the curve metrics. It is, therefore, a promising method for early CKD prediction. The experimental results showed that Urine protein and creatinine ratio (UPCR), Proteinuria (PRO), Red blood cells (RBC), Glucose Fasting (GLU), Triglycerides (TG), Total Cholesterol (T-CHO), age, and gender are important risk factors. CKD care is closely related to primary care level and is recognized as a healthcare priority in national strategy. The proposed risk prediction models can support the important influence of personality and health examination representations in predicting early CKD.

Background Our study aimed to determine the association between homocysteine levels and cardiovascular disease (CVD) risk in middle-aged and elderly adults in a community in northern Taiwan. Methods Participants in our study included adults aged 50 to 85 years old during community health examinations in 2019. A total of 396 people were enrolled, the ethnicity of all participants is Chinese. We divided participants according to tertiles of ln[homocysteine] level (low, middle and high groups). The CVD risk was calculated by the Framingham cardiovascular risk score (FRS). An FRS ≥ 20% indicated high CVD risk. Pearson correlation coefficients were calculated between homocysteine level and other cardio-metabolic risk factors while adjusting for age. Multivariate logistic regression analysis was used to determine the association of high and middle ln[homocysteine] groups with high CVD risk after adjusting age, sex, uric acid, creatinine, and body mass index (BMI). The Youden index and receiver operating characteristic (ROC) curves were performed to determine the optimized cut-off value. Results There were 396 people enrolled for analysis; 41.4% of participants were male, and the average age was 64.79 (± 8.76). In our study, we showed a positive correlation of homocysteine with FRS. In the logistic regression models, higher ln[homocysteine] levels was associated with higher CVD risk with a odds ratio (OR) of 2.499 and 95% confidence interval (CI) of 1.214 to 5.142 in the high homocysteine level group compared with the low homocysteine group after adjusting for traditional CVD risk factors. The area under the ROC curve was 0.667, and a ln[homocysteine] cut-off value of 2.495 µmol/L was determined. Conclusions Middle-aged and elderly people with increased homocysteine levels were associated with higher FRSs in this Taiwan community. Furthermore, homocysteine was an independent risk factor for high CVD risk in this study.

Previous studies on CKD patients have mostly been retrospective, cross-sectional studies. Few studies have assessed the longitudinal assessment of patients over an extended period. In consideration of the heterogeneity of CKD progression. It’s critical to develop a longitudinal diagnosis and prognosis for CKD patients. We proposed an auto Machine Learning (ML) scheme in this study. It consists of four main parts: classification pipeline, cross-validation (CV), Taguchi method and improve strategies. This study includes datasets from 50,174 patients, data were collected from 32 chain clinics and three special physical examination centers, between 2015 and 2019. The proposed auto-ML scheme can auto-select the level of each strategy to associate with a classifier which finally shows an acceptable testing accuracy of 86.17%, balanced accuracy of 84.08%, sensitivity of 90.90% and specificity of 77.26%, precision of 88.27%, and F1 score of 89.57%. In addition, the experimental results showed that age, creatinine, high blood pressure, smoking are important risk factors, and has been proven in previous studies. Our auto-ML scheme light on the possibility of evaluation for the effectiveness of one or a combination of those risk factors. This methodology may provide essential information and longitudinal change for personalized treatment in the future.

Background Our study aimed to determine the association between homocysteine levels and cardiovascular disease (CVD) risk in middle-aged and elderly adults in a community in northern Taiwan.MethodsParticipants in our study included adults aged 50 to 85 years old during community health examinations on 2019. A total of 396 people were enrolled. We divided participants according to tertiles of homocysteine level (low, middle and high groups). The CVD risk was calculated by the Framingham cardiovascular risk score (FRS). An FRS ≥ 20% indicated high CVD risk. Pearson correlation coefficients were calculated between homocysteine level and other cardio-metabolic risk factors while adjusting for age. High CVD risk in the middle and high homocysteine groups was compared with that in the low homocysteine group by multivariate logistic regression with adjustments for age, sex, smoking, hypertension (HTN), diabetes mellitus (DM), body mass index (BMI) and hyperlipidemia. The Youden index and receiver operating characteristic (ROC) curves were performed to determine the optimized cut-off value.ResultsThere were 396 people enrolled for analysis; 41.4% of participants were male, and the average age was 63.72 (±8.76). In our study, we showed a positive correlation of homocysteine with FRS. In the logistic regression models, the prevalence of high CVD risk was increased as homocysteine increased. The odds ratio (OR) and 95% confidence interval for high CVD risk was 2.851 (1.402 to 5.801) in the high homocysteine level group compared with the low homocysteine group after adjusting for traditional CVD risk factors (P=0.004). The area under the ROC curve was 0.67, and a homocysteine cut-off value of 12.15 µmol/L was determined.ConclusionsMiddle-aged and elderly people with increased homocysteine levels were associated with higher FRSs in this Taiwan community. Furthermore, homocysteine was an independent risk factor for high CVD risk in this study.