Abstract Queens University Belfast, the Belfast Health Trust and Randox Laboratories are working together to create risk and diagnostic classifiers for patients with haematuria. Biomarker profiles may fail to differentiate between all possible causes of hematuria, but it would be a huge advancement if benign and malignant causes were differentiated. Our objective was to determine whether single biomarkers or multivariate algorithms could significantly improve on the predictive power of an algorithm based on demographics for detection of urothelial cancer in patients presenting with hematuria. We collected demographic and clinical information from 157 patients (80 urothelial cancers and 77 with confounding pathologies) who had presented with hematuria and were recruited to a case control study. For each patient we measured 22 urinary biomarkers and serum Carcinoembryonic antigen (CEA) using either ELISAs or the Randox biochip technology, BAT. We analysed the collated data, using Forward Wald binary logistic regression analyses. Algorithms based on demographic variables were designated as Prior Predicted Probability (PPP). We then created algorithms incorporating PPP as a single variable, together with biomarkers.We determined Areas under the Receiver Operating Characteristic (AUROC) for differentially expressed single biomarkers and multivariate algorithms. AUROC for CEA, Bladder Tumour Antigen (BTA) and Nuclear matrix protein (NMP22) = 0.74; 0.74; and 0.79, respectively. Vascular endothelial growth factor, dDimer, Fas, hyaluronidase, interleukin(IL) IL-1α, IL-6 and IL-8 were also differentially expressed (T-test; p < 0.05). PPP included age and smoking years. In combination, PPP, NMP22 and Epidermal Growth Factor (EGF) achieved AUROC = 0.90, significantly improving upon the AUROC for PPP which was 0.76. Although neutrophil-associated gelatinase lipocalin (NGAL) levels were similar in urines from UC and control patients, a multivariate classifier which comprised age, serum CEA and urinary NGAL and interleukin 8 achieved a respectable AUROC = 0.844. Biomarkers significantly improved upon the AUROC statistic based on demographics. Despite non differential urinary levels across UC and controls, NGAL made a significant contribution to a diagnostic classifier exemplifying the unpredictable nature of the complexities involved in collectives of biomarkers. The impact of biomarkers in multivariate algorithms for bladder cancer diagnosis in patients with hematuria. Abogunrin F, O'Kane HF, Ruddock MW, Stevenson M, Reid CN, O'Sullivan JM, Anderson NH, O'Rourke D, Duggan B, Lamont JV, Boyd RE, Hamilton P, Nambirajan T, Williamson KE. Cancer. May 15;118(10) [2012] American Cancer Society Inc Citation Format: Michael Stevenson, Cherith Reid, Brian Duggan, Mark Ruddock, Kate E. Williamson. Bladder cancer diagnostic algorithms in hematuria populations. [abstract]. In: Proceedings of the 104th Annual Meeting of the American Association for Cancer Research; 2013 Apr 6-10; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2013;73(8 Suppl):Abstract nr 5136. doi:10.1158/1538-7445.AM2013-5136