(1) Background: Increasing evidence indicates that lipid metabolism may influence the concentration of prostate-specific antigen (PSA). However, the association between triglycerides and PSA remains unclear and complicated. Hence, we evaluated the correlation between triglycerides and PSA based on the U.S. National Health and Nutrition Examination Survey (NHANES) database. (2) Methods: A total of 2910 participants out of 41,156 participants fit into our study after conducting the screening from the 2003 to 2010 NHANES survey. Serum triglycerides were the independent variable of our study, and PSA was the dependent variable; (3) Results: In our study, the average age of chosen participants was 59.7 years (±12.7). After adjusting for covariates, the result indicated that for each additional unit of serum triglyceride (mg/dL), the PSA concentrations were reduced by 0.0043 ng/mL (-0.0082, -0.0005) with a statistical difference. Furthermore, we used machine learning of the XGBoost model to determine the relative importance of selected variables as well as constructed a smooth curve based on the fully adjusted model to investigate the possible linear relationship between the triglyceride and PSA concentrations. (4) Conclusions: The serum triglyceride is independently and negatively correlated with PSA among American males, which may make it hard to detect asymptomatic prostate cancer and diagnose at an advance stage with higher triglycerides due to detection bias.
Keywords: National Health and Nutrition Examination Survey (NHANES); machine learning; prostate cancer; prostate-specific antigen; triglycerides.