Abstract

Prostate cancer remains a major global health burden and one of the leading causes of cancer-related death in men worldwide. Early detection continues to be challenging because conventional screening tools, including prostate-specific antigen (PSA) testing and digital rectal examination (DRE), have limited specificity and may lead to inconsistent clinical decision-making. In this context, multiparametric and biparametric MRI have shown promise for improving risk stratification, although their performance may be further enhanced through integration with emerging molecular approaches. This review examines recent advances in the early detection of prostate cancer, with a focus on novel biomarkers, multi-omics strategies, and artificial intelligence (AI). Emerging biomarkers include molecular, cellular, genetic, and exosomal candidates such as non-coding RNAs, urinary exosomal mRNA, prostate cancer stem cell-related markers, ancestry-associated SNPs, polygenic risk scores, and blood-based tools such as the 4Kscore. These approaches may improve the identification of clinically significant disease and provide more personalized risk assessment. In parallel, AI-based methods, including machine learning and deep learning, are increasingly being applied to MRI interpretation, biomarker discovery, risk prediction, and multi-omics data integration. Together, these strategies have the potential to support earlier and more precise detection of prostate cancer across diverse populations. However, broader clinical implementation will depend on further validation, standardization, and assessment of their applicability in real-world settings.

Keywords

prostate cancer, early detection, biomarkers, multi-omics, artificial intelligence, prostate-specific antigen, magnetic resonance imaging, polygenic risk score, health disparities