Search

Purpose: We assessed the risk of gout in the Taiwan Biobank population by applying various machine learning algorithms. The study aimed to identify crucial risk factors and evaluate the performance of different models in gout prediction. Patients and Methods: This study analyzed data from 88,210 individuals in the Taiwan Biobank, identifying 19,338 cases of gout and 68,872 controls. After data cleaning and propensity score matching for gender and age, the final analytical sample comprised 38,676 individuals (19,338 gout cases and 19,338 controls). Five machine learning models were used: Bayesian Network (BN), Random Forest (RF), Gradient Boosting (GB), Logistic Regression (LR), and Neural Network (NN). The predictive performance was evaluated using a split dataset (80% training set and 20% test set). Results: Variable importance analysis was performed to identify key variables, with uric acid and gender emerging as the most influential risk factors. Descriptive data highlighted significant differences between the control group and gout patients, with a higher prevalence of gout in men (51.36% vs 48.64%). Both the RF and GB demonstrated high performance across multiple metrics, with RF consistently achieving a high area under the curve (AUC) of 0.986 to 0.987, alongside excellent sensitivity (0.945– 0.947) and specificity (0.998– 0.999). GB also performed robustly, with AUC values around 0.987– 0.988 and maintaining high sensitivity (0.944– 0.950) and specificity (0.995– 0.999) across different model variations. The F1 scores for both models (GB and RF) indicate strong predictive capabilities, with values around 0.971– 0.972. Conclusion: The RF and GB demonstrated exceptional accuracy in predicting gout status, particularly when incorporating genetic data alongside clinical factors. These findings underscore the potential for integrating machine learning models with genetic information to enhance gout prediction accuracy in clinical practice. [ABSTRACT FROM AUTHOR]

Background: Parkinson's disease (PD) is a complex neurodegenerative disease with an elusive etiology that involves the interaction between genetic, behavioral, and environmental factors. Recently, epigenetic modifications, particularly DNA methylation, have been recognized to play an important role in the onset of PD. Glycoprotein non-metastatic melanoma protein B (GPNMB), a type I transmembrane protein crucial for immune cell activation and maturation, has emerged as a potential biomarker for the risk of PD. This research aims to investigate the influence of exercise and gender on the regulation of methylation levels of GPNMB cg17274742 in individuals. Methods: We analyze data from 2,474 participants in the Taiwan Biobank, collected from 2008 and 2016. Methylation levels at the GPNMB cg17274742 CpG site were measured using Illumina Infinium MethylationEPIC beads. After excluding individuals with incomplete data or missing information on possible risk factors, our final analysis included 1,442 participants. We used multiple linear regression models to assess the association between sex and exercise with adjusted levels of GPNMB cg17274742 for age, BMI, smoking, drinking, coffee consumption, serum uric acid levels, and hypertension. Results: Our results demonstrated that exercise significantly influenced the methylation levels of GPNMB cg17274742 in males (β = -0.00242; p = 0.0026), but not in females (β = -0.00002362; p = 0.9785). Furthermore, male participants who exercised showed significantly lower levels of methylation compared to the reference groups of the female and non-exercising reference groups (β = -0.00357; p = 0.0079). The effect of the interaction between gender and exercise on the methylation of GPNMB cg17274742 was statistically significant (p = 0.0078). Conclusion: This study suggests that gender and exercise can modulate GPNMB cg17274742, with hypomethylation observed in exercise men. More research is needed to understand the underlying mechanisms and implications of these epigenetic changes in the context of risk and prevention strategies. [ABSTRACT FROM AUTHOR]

In various cross-sectional and longitudinal studies, exercise has been associated with cardiometabolic outcomes, including high-density lipoprotein (HDL) cholesterol. Exercise-induced changes in HDL cholesterol seem to be affected by genetic polymorphisms. In this study, we examined whether variant APOE rs7412 is involved in the association between HDL cholesterol and exercise. From adults assessed in Taiwan Biobank (TWB) between 2008 and 2019, we analyzed data from 57,638 normolipidemic subjects. To examine the association between exercise, APOE rs7412, and HDL cholesterol, a multiple linear regression model was used. A higher HDL was associated with both aerobic exercise (regression coefficient [mg/dL] beta- (β), 1.112; 95% confidence interval (CI); 0.903-1.322) and resistance exercise (β, 2.530; 95% CI, 2.093-2.966). In comparison with the APOE rs7412-CC genotype, the β was 2.589 (95% CI, 2.329-2.848) among those with the CT + TT genotype. Compared to adults who had the CC genotype and did not exercise (the CC/no exercise group), the β-coefficient determined for the different genotype and exercise groups was 1.135 (95% CI, 0.911-1.359) for the CC genotype and aerobic exercise group, 2.753 (95% CI, 2.283-3.322) for the CC genotype and resistance exercise group, 2.705 (95% CI, 2.390-3.020) for the CT + TT genotype and no exercise group, 3.682 (95% CI, 3.218-4.146) for the CT + TT genotype and aerobic exercise group, and 3.855 (95% CI, 2.727-4.982) for the CT + TT genotype and resistance exercise group, respectively. This study demonstrates that self-reported aerobic and resistance exercise both raised HDL levels, yet resistance exercise was associated with a greater increase, particularly among Taiwanese subjects carrying the APOE rs7412-CT+TT genotype. [ABSTRACT FROM AUTHOR]