Molecular characterizaion of neuroendocrine-like bladder cancer

Neuroendocrine bladder cancer is an aggressive variant of bladder cancer with significant metastatic potential and high risk of mortality. Diagnosis of these tumors is currently dependent on morphological criteria and staining for neuroendocrine markers. Using machine learning and multiple validation cohorts in different clinical settings, we developed a model that identifies tumors with transcriptomic profiles consistent with NE bladder cancers with an absence of NE features by morphological criteria. Early and accurate identification of these patients by genomic analysis may improve outcomes through treatment intensification and adaptation of standard treatment regimens. In this study, we used transcriptome-wide expression profiles to generate a single-sample classifier to identify neuroendocrine-like muscle-invasive bladder tumors.  The classifier was validated on six independent cohorts, including a radical cystectomy cohort of 256 bladder cancer cases.