Ricardo de Matos Simoes¹, F Emmert-Streib², Brian Duggan³, Mark W Ruddock⁴*, Declan O’Rourke⁵, Hugh F O’Kane⁶, Funso Abogunrin⁶, Cherith N Reid⁴, John V Lamont⁴, Peter Fitzgerald⁴ and Kate E Williamson⁷

¹Dana Farber Cancer Institute, Brookline Avenue, Boston, USA
²Institute of Biosciences and Medical Technology, Finland
³Department of Urology, Ulster Hospital Dundonald, BT16 1RH, Northern Ireland, UK
⁴Randox Laboratories Ltd, Crumlin, BT29 4QY, Northern Ireland, UK
⁵Department of Pathology, Belfast City Hospital, BT9 7AB, Northern Ireland, UK
⁶Department of Urology, Belfast City Hospital, BT9 7AB, Northern Ireland, UK
⁷Centre for Cancer Research and Cell Biology, Queen's University Belfast, BT7 1NN, Northern Ireland, UK

*Corresponding Author: Mark W Ruddock, Randox Laboratories Ltd, Crumlin, BT29 4QY, Northern Ireland, UK.

Received: June 05, 2021; Published: July 14, 2021

Abstract

Background: There is an urgent clinical need for evidence-based risk stratification modalities because of the increased prevalence of haematuria in the aging population. Currently, urothelial cancer (UC) classifiers have insufficient diagnostic accuracy to inform clinical decisions. Therefore, there is an urgent need for new tests which can at least stratify and if possible, be diagnostic.

Methods: To study patient characteristics associated with misclassification by UC diagnostic classifiers we analysed data collected from 156 patients recruited to a case control study between November 2006 and October 2008. First, we undertook a random forest classification based on measurements of 29 protein biomarkers measured in urine, serum and plasma and urinary creatinine, osmolality and protein. Second, we used random subsampling to generate 1000 training and test patient datasets and then estimated probabilities of correct, incorrect and inconsistent classification for each patient as either control or UC based on their hypergeometric distribution. Third, we identified clinical variables associated with incorrect classification using Fisher’s exact test.

Results: One hundred patients were classifiable, 46 non-classifiable and 10 inconsistently classifiable. Common confounders included smoking, age, grade, stage, AH medication, dipstick analyses, history of BPE, cytology diagnosis and presence/absence of inflammatory cells in cytology. Five patients with newly diagnosed prostate or kidney cancer and seven with “no diagnosis” were misclassified as UC. Sixteen ≥ pT2 and 24/47 pTa stage tumours were classifiable; 21 pTa tumours were non-classifiable and two were inconsistently classified.

Conclusion: Patients classified as UC require urgent referral; patients classified as controls > 65 years or smokers should also be referred because of their risk of early stage UC. Patients classified as controls who were non-smokers and ≤ 65 years were low risk. Our novel classification approach could increase understanding about the application of diagnostic classifiers in many complex diseases.

Keywords: Age; Biomarkers; Classification; Inflammatory Cells; Logistic Regression; Random Forest; Predictive Classifiers; Smoking

References

1. Margulis V and Sagalowsky AI. “Assessment of hematuria”. Medical Clinics of North America 95 (2011): 153-159.
2. Abogunrin F., et al. “The impact of biomarkers in multivariate algorithms for bladder cancer diagnosis in patients with hematuria”. Cancer 118 (2012): 2641-2650.
3. Edwards TJ., et al. “A prospective analysis of the diagnostic yield resulting from the attendance of 4020 patients at a protocol-driven haematuria clinic”. BJU International 97 (2006): 301-305.
4. Khadra MH., et al. “A prospective analysis of 1,930 patients with hematuria to evaluate current diagnostic practice”. Journal of Urology 163 (2000): 524-527.
5. Fradet Y and Lockhard C. “Performance characteristics of a new monoclonal antibody test for bladder cancer: ImmunoCyt trade mark”. Canadian Journal of Urology 4 (1997): 400-405.
6. Malkowicz SB. “The application of human complement factor H-related protein (BTA TRAK) in monitoring patients with bladder cancer”. Urologic Clinics of North America 27 (2000): 63-73.
7. Moonen PM., et al. “Urinary NMP22 BladderChek test in the diagnosis of superficial bladder cancer”. European Urology 48 (2005): 951-856.
8. Leyh H., et al. “Results of a European multicenter trial comparing the BTA stat Test to urine cytology in patients suspected of having bladder cancer”. Journal of Urology 157 (1997): 337A.
9. Johnston B., et al. “Rapid detection of bladder cancer: a comparative study of point of care tests”. Journal of Urology 158 (1997): 2098-101.
10. Lotan Y., et al. “Bladder cancer screening in a high risk asymptomatic population using a point of care urine-based protein tumor marker”. Journal of Urology 182 (2009): 52-58.
11. Kim WJ., et al. “Predictive value of progression-related gene classifier in primary non-muscle invasive bladder cancer”. Molecular Cancer 9 (2010): 3.
12. Gui Y., et al. “Frequent mutations of chromatin remodeling genes in transitional cell carcinoma of the bladder”. Nature Genetics 43 (2011): 875-878.
13. Goodison S., et al. “Urinary proteomic profiling for diagnostic bladder cancer biomarkers”. Expert Review on Proteomics 6 (2009): 507-514.
14. Hyndman ME., et al. “Metabolomics and bladder cancer”. Urology and Oncology 29 (2011): 558-561.
15. Burger M., et al. “Epidemiology and risk factors of urothelial bladder cancer”. European Urology 63 (2013): 234-241.
16. Fitzgerald SP., et al. “Development of a high-throughput automated analyzer using biochip array technology”. Clinical Chemistry 51 (2005): 1165-1176.
17. Dobson AJ. “An Introduction to Generalized Linear Models”. Second Edition, ed. 3rd: Chapman and Hall/CRC 2008.
18. Fawcett T. “An introduction to ROC analysis”. Pattern Recognition Letters 27 (2006): 861-874.
19. Breiman L. “Random Forests”. Machine Learning 45 (2001): 5-32.
20. Benjamini Y and Hochberg Y. “Controlling the false discovery rate: a practical and powerful approach to multiple testing”. Journal of the Royal Statistical Society, Series B (Methodological) 57 (1995): 125-133.
21. Linden M., et al. “Tumour expression of bladder cancer-associated urinary proteins”. BJU International (2013).
22. Alexander JC., et al. “Effect of age and cigarette smoking on carcinoembryonic antigen levels”. JAMA 235 (1976): 1975-1979.
23. Goldstein MJ and Mitchell EP. “Carcinoembryonic antigen in the staging and follow-up of patients with colorectal cancer”. Cancer Investigation 23 (2005): 338-351.
24. Hegele A., et al. “CA19.9 and CEA in transitional cell carcinoma of the bladder: serological and immunohistochemical findings”. Anticancer Research 30 (2010): 5195-5200.
25. Schlomer BJ., et al. “Prospective validation of the clinical usefulness of reflex fluorescence in situ hybridization assay in patients with atypical cytology for the detection of urothelial carcinoma of the bladder”. Journal of Urology 183 (2010): 62-67.
26. Rantalainen M., et al. “Accounting for control mislabeling in case-control biomarker studies”. Journal of Proteome Research 10 (2011): 5562-5567.

Citation

Citation: Mark W Ruddock., et al. “Confounding Effects of Heterogeneity and the Impact on the Accuracy of Urothelial Cancer Classifiers for Haematuria Patients”.Acta Scientific Medical Sciences 5.8 (2021): 33-46.

Copyright

Copyright: © 2021 Mark W Ruddock., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.