[Correlation between oxidative balance score and benign prostatic hyperplasia assessed by machine learning].

Abstract

Objective: The relationship between benign prostatic hyperplasia (BPH) and the oxidative balance score (OBS) will be discussed in this study.

Methods: The clinical data on 16 dimensions of diet and 4 dimensions of lifestyle from the National Health and Nutrition Examination Survey (NHANES) from 2001 to 2008 were used to calculate OBS. We considered BPH as the outcome and investigated the linear and nonlinear relationships between the two. Additionally, subgroup analyses and interaction tests were conducted as well. Furthermore, the methods of machine learning including XGBoost, support vector machine (SVM) and naive Bayes (NB) were used to establish a predictive model for BPH.

Results: Higher OBS was consistently associated with an increased prevalence of BPH, with Restricted Cubic Splines highlighting a significant positive nonlinear association (P=0.015). Subgroup analyses revealed differences and interactive relationships based on alcohol consumption. Among the seven machine learning models that we included the OBS score in, the XGBoost model emerged as the best, with an AUC value of 0.769.

Conclusion: There is a significant association between OBS and the prevalence of BPH in the American population, which provides a valuable insight for further diagnosis and research of the disease.