Development of a multivariable risk model integrating urinary peptide metabolites and Extracellular Vesicle RNA data to detect significant prostate cancer

The aim of this study was to investigate whether the robust integration of expression data from urinary extracellular vesicle RNA (EV-RNA) with urine proteomic metabolites can accurately predict PCa biopsy outcome. Urine samples were analyzed by mass spectrometry and NanoString gene-expression analysis. As a result, four classifiers were generated: ‘MassSpec’ (CE-MS proteomics), ‘EV-RNA’, ‘SoC’ (standard of care) and ‘ExoSpec’. The best prediction for Gs³3+4 at initial biopsy (AUC=0.83, 95% CI:0.77-0.88) was achieved by applying ‘ExoSpec’ classifier and he outperformed other predictive classifiers. In addition, the results showed that the performance of ‘ExoSpec’ could reduce unnecessary biopsies by 30%.