Design of Machine Learning Algorithms and Internal Validation of a Kidney Risk Prediction Model for Type 2 Diabetes Mellitus.

Objective: This study aimed to explore specific biochemical indicators and construct a risk prediction model for diabetic kidney disease (DKD) in patients with type 2 diabetes (T2D). Methods: This study included 234 T2D patients, of whom 166 had DKD, at the First Hospital of Jilin University from January 2021 to July 2022. Clinical characteristics, such as age, gender, and typical hematological parameters, were collected and used for modeling. Five machine learning algorithms [Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF)] were used to identify critical clinical and pathological features and to build a risk prediction model for DKD. Additionally, clinical data from 70 patients (nT2D = 20, nDKD = 50) were collected for external validation from the Third Hospital of Jilin University. Results: The RF algorithm demonstrated the best performance in predicting progression to DKD, identifying five major indicators: estimated glomerular filtration rate (eGFR), glycated albumin (GA), Uric acid, HbA1c, and Zinc (Zn). The prediction model showed sufficient predictive accuracy with area under the curve (AUC) values of 0.960 (95% CI: 0.936-0.984) and 0.9326 (95% CI: 0.8747-0.9885) in the internal validation set and external validation set, respectively. The diagnostic efficacy of the RF model (AUC = 0.960) was significantly higher than each of the five features screened with the highest feature importance in the RF model. Conclusion: The online DKD risk prediction model constructed using the RF algorithm was selected based on its strong performance in the internal validation.

Endothelial nitric oxide synthase gene polymorphisms and risk of erectile dysfunction: An updated meta-analysis of genetic association studies.

PURPOSE: Endothelial nitric oxide synthase (eNOS) polymorphisms have been implicated as risk factors for erectile dysfunction (ED), but the results of genetic association studies are inconclusive. We performed a meta-analysis of published studies investigating the association between ED and three eNOS polymorphisms, intron 4 VNTR, G894T and T786C in humans. METHODS: The PubMed, Web of Science, CNKI and Google Scholar databases were searched for relevant studies published up to November 2017. Association studies with case-control design were included. For each study with genotype information we calculated odds ratios (OR) and 95% confidence intervals (CI). RESULTS: The search identified 13 eligible studies. The G894T and T786C polymorphisms showed a significant association with ED risk in Caucasians (GT + TT versus GG for G894T: OR = 2.13, 95% CI = 1.08-4.19; CC versus CT + TT for T786C: OR = 3.29, 95% CI = 2.30-4.72) and Asians (GT + TT versus GG for G894T: OR = 2.08, 95% CI = 1.53-2.84; CC + CT versus TT for T786C: OR = 3.13, 95% CI = 1.35-7.25). In addition, the intron 4 VNTR polymorphism was associated with ED risk only among Caucasian subjects (aa versus bb + ab: OR = 2.38, 95% CI = 1.15-4.93). We found no evidence of publication bias. The robustness of overall analyses was ensured in sensitivity analyses excluding studies deviating from Hardy-Weinberg equilibrium. CONCLUSION: Our findings suggest that common genetic polymorphisms in the eNOS gene contribute to risk of ED, presumably by effects on eNOS activity and NO availability.

Establishment of age- and gender-specific pediatric reference intervals for liver function tests in healthy Han children.

BACKGROUND: The development and growth of children influence values of liver function tests. This study aims to establish age- and gender-specific pediatric reference intervals of liver function among Han children in Changchun, China. METHODS: A total of 1394 healthy Han children, aged 2-14 years, were recruited from communities and schools with informed parental consent in Changchun. The levels of serum alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyltransferase (GGT), alkaline phosphatase (ALP), total protein (TP), albumin (ALB), total bilirubin (TBIL) and direct bilirubin (DBIL) were measured on Hitachi 7600-210 automatic biochemical analyzer. The age- and gender-specific reference intervals were partitioned using Harris and Boyd's test and calculated using nonparametric rank method. The pediatric reference intervals were validated in five representative hospitals located in different areas in Changchun. RESULTS: All the analytes required some levels of age partitioning. Proteins (TP, ALB) and bilirubins (TBIL, DBIL) required no gender partitioning. In contrast, considerable gender partitioning was required for serum ALT, AST, GGT, and ALP. TP, TBIL, and DBIL showed steady increases, and AST showed apparent decreases over time, whereas ALT, GGT, ALP, and ALB demonstrated complex trends of change. ALT and GGT increased sharply in males from 11 to 14 years old. However, ALP declined in females from 13 to 14 years. All five laboratories passed the validation of reference intervals. CONCLUSIONS: There were apparent age or gender variations of the reference intervals for liver function. When establishing pediatric reference intervals, partitioning according to age and gender is necessary.