Prostate cancer, benign prostatic hyperplasia, and prostatitis share substantial overlap in clinical symptoms and biological characteristics, which hampers non-invasive and early differential diagnosis. Untargeted metabolomics enables comprehensive profiling of disease-associated metabolic alterations; however, its high dimensionality and strong feature correlations challenge conventional statistical approaches.
To address this, we analyzed serum untargeted LC-MS data following standardized preprocessing. We adopted a nested cross-validation strategy to evaluate various feature selection methods and machine learning classifiers, ultimately determining that multiclass LASSO regression was the most effective feature selection approach.
An optimized Random Forest model demonstrated strong, superior performance in distinguishing between prostate cancer, prostatitis, benign prostatic hyperplasia, and healthy controls (out-of-fold accuracy: 93.8%; macro-F1: 0.937). Additionally, SHAP (SHapley Additive exPlanations) analysis translated feature statistical importance into biologically meaningful modules, revealing that distinct, disease-specific patterns of metabolic reprogramming drove the model's robust multiclass discrimination.
This study demonstrates the value of integrating serum untargeted metabolomics with advanced explainable machine learning for effective multiclass differentiation of major prostate diseases, providing a promising non-invasive framework for diagnostic stratification and metabolic biomarker discovery.
Metabolites. 2026 Mar 31*** epublish ***
Zijie Wang, Jialu Xin, Qiuyan He, Shutong Xu, Jinghan Wu, Fang Yang, Liang Dong
School of Medical and Life Sciences, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China., School of Acupuncture and Tuina, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China., School of Health Preservation and Rehabilitation, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China.