Interpretable machine learning identifies metabolites associated with glomerular filtration rate in type 2 diabetes patients.

Objective: The co-occurrence of kidney disease in patients with type 2 diabetes (T2D) is a major public health challenge. Although early detection and intervention can prevent or slow down the progression, the commonly used estimated glomerular filtration rate (eGFR) based on serum creatinine may be influenced by factors unrelated to kidney function. Therefore, there is a need to identify novel biomarkers that can more accurately assess renal function in T2D patients. In this study, we employed an interpretable machine-learning framework to identify plasma metabolomic features associated with GFR in T2D patients. Methods: We retrieved 1626 patients with type 2 diabetes (T2D) in Liaoning Medical University First Affiliated Hospital (LMUFAH) as a development cohort and 716 T2D patients in Second Affiliated Hospital of Dalian Medical University (SAHDMU) as an external validation cohort. The metabolite features were screened by the orthogonal partial least squares discriminant analysis (OPLS-DA). We compared machine learning prediction methods, including logistic regression (LR), support vector machine (SVM), random forest (RF), and eXtreme Gradient Boosting (XGBoost). The Shapley Additive exPlanations (SHAP) were used to explain the optimal model. Results: For T2D patients, compared with the normal or elevated eGFR group, glutarylcarnitine (C5DC) and decanoylcarnitine (C10) were significantly elevated in GFR mild reduction group, and citrulline and 9 acylcarnitines were also elevated significantly (FDR<0.05, FC > 1.2 and VIP > 1) in moderate or severe reduction group. The XGBoost model with metabolites had the best performance: in the internal validate dataset (AUROC=0.90, AUPRC=0.65, BS=0.064) and external validate cohort (AUROC=0.970, AUPRC=0.857, BS=0.046). Through the SHAP method, we found that C5DC higher than 0.1µmol/L, Cit higher than 26 µmol/L, triglyceride higher than 2 mmol/L, age greater than 65 years old, and duration of T2D more than 10 years were associated with reduced GFR. Conclusion: Elevated plasma levels of citrulline and a panel of acylcarnitines were associated with reduced GFR in T2D patients, independent of other conventional risk factors.

Explainable Machine Learning-Based Prediction Model for Diabetic Nephropathy.

The aim of this study is to analyze the effect of serum metabolites on diabetic nephropathy (DN) and predict the prevalence of DN through a machine learning approach. The dataset consists of 548 patients from April 2018 to April 2019 in the Second Affiliated Hospital of Dalian Medical University (SAHDMU). We select the optimal 38 features through a least absolute shrinkage and selection operator (LASSO) regression model and a 10-fold cross-validation. We compare four machine learning algorithms, including extreme gradient boosting (XGB), random forest, decision tree, and logistic regression, by AUC-ROC curves, decision curves, and calibration curves. We quantify feature importance and interaction effects in the optimal predictive model by Shapley additive explanation (SHAP) method. The XGB model has the best performance to screen for DN with the highest AUC value of 0.966. The XGB model also gains more clinical net benefits than others, and the fitting degree is better. In addition, there are significant interactions between serum metabolites and duration of diabetes. We develop a predictive model by XGB algorithm to screen for DN. C2, C5DC, Tyr, Ser, Met, C24, C4DC, and Cys have great contribution in the model and can possibly be biomarkers for DN.

National Nutrition and Health Systematic Survey for Children 0-17 Years of Age in China / 生物医学与环境科学（英文）

The main purpose of the National Nutrition and Health Systematic Survey for children 0-17 years of age in China (CNHSC) was to collect basic data on the nutrition, development, and health status for children in different regions across China using evidence-based, reliable, and cost-effective approaches. Children and their parents or guardians from seven regions (south, southwest, north, northwest, eastern, central, and northeast China) in China were recruited. A multi-stage stratified randomized sampling method was used. Two provinces were randomly sampled from each of the seven regions, from which one urban district and one rural country were also randomly sampled, resulting in a total of 28 survey counties/districts. Dietary surveys, health examinations, laboratory testing, and questionnaires were used to collect dietary intake, nutritional status, child development, and health status information. Nutrition, health, and lifestyle assessment of children and their parents was determined using the Knowledge Attitude Practice (KAP) survey. Greater than 100,000 children (38,000 children < 6 years of age and 66,000 children 6-17 years of age) completed the survey. The survey provided comprehensive data on child nutrition and health status for future studies and will serve as the basis for an integrated nutrition and health improvement strategies proposal for children in China.

The Patterns of Complementary Feeding and Growth among 12 to 23 Month-Old Children in China / 生物医学与环境科学（英文）

Objective@#This study aimed to understand the characteristics of dietary patterns among children aged 12 to 23 months and discusses the relationship between dietary patterns and the growth of children.@*Method@#Cross-sectional data were selected from the National Nutrition and Health Systematic Survey for 0 to 18 year-old children in China ( @*Results@#Four dietary patterns were identified among the children @*Conclusion@#Although China is undergoing rapid urbanization and economic development, there is still a phenomenon of insufficient intake of protein-rich foods and dairy-based dietary patterns at the stage of complementary food introduced among children aged 12 to 23 months.

Endoscopic submucosal excavation as the derivative technology of endoscopic submucosal dissection for the treatment of intestinal neuroendocrine tumor / 中国内镜杂志

Objective To investigate the therapeutic effect and safety of ESE (endoscopic submucosalexcavation) as the derivative technology of ESD (endoscopic submucosal dissection) for intestinal Neuroendocrinetumor. Methods A total of 23 lesions diagnosed as Neuroendocrine tumor were treated by ESE. Pathologicaldiagnosis was performed. Reverse events were recorded.Patients were followed up for recurrence andmetastasis. Results Lesions, 0.4 ~ 3.0 cm (medium size 1.0 cm) in diameter,were all resected at one ESE procedure.The operation time was 20 ~ 75 min (medium 30 min). Postoperative bleeding occurred in one case .Initiative fullthickness resection was made in one case due to the violation of muscularis propria layer. 23 cases were histologicallydiagnosed as neuroendocrine tumor, with 21 as G1 and 2 as G2, none as G3. Within 3 gastric neuroendocrine tumors,2 were type 1 and 1 was type 2. All resected samples were free of residual tumor cell in the lateral and basalmargins. Conclusion ESE is safe and efficacious for the treatment of intestinal neuroendocrine tumor.