Clinicopathologic calculators for bladder cancer (BC) provide only moderate prognostic accuracy and do not capture the underlying molecular phenotypes. Herein, we applied capillary electrophoresis-mass spectrometry (CE-MS) to identify prognostic signatures in urine linked to BC outcome. In a discovery cohort (n = 131; mean follow-up 623 days), 114 survival-associated peptides were significant prognostic factors for overall survival (OS) and were integrated into, and optimized as a 110-peptide support vector machine (SVM) classifier (BC110). Validation of the BC110 classifier was performed in an independent cohort (n = 102; mean follow-up 1605 days), resulting in an AUC of 0.78 (p = 0.03). Functional enrichment analysis revealed that the BC110 peptide panel predominantly reflects extracellular matrix (ECM) remodeling and collagen-related pathways, alongside additional biological processes including coagulation, complement activation, oxidative stress, and RNA processing, consistent with active tumor-stroma crosstalk. This urine-based classifier enables non-invasive risk stratification and may complement guideline calculators by identifying high-risk patients for adjuvant therapy and low-risk groups for reduced surveillance, potentially lowering reliance on repeated cystoscopy.
Keywords: biomarker classifier; bladder cancer; capillary electrophoresis–mass spectrometry (CE–MS); collagen; extracellular matrix (ECM); survival prediction; urinary peptidomics.
© 2026 Wiley‐VCH GmbH.