Collectives of diagnostic biomarkers identify high-risk subpopulations of hematuria patients: exploiting heterogeneity in large-scale biomarker data

BMC Medicine

Kate E Williamson³  Thiagarajan Nambirajan¹  Neil H Anderson²  Declan O'Rourke⁴  Hugh F O'Kane¹  Lisa White³  Owen Roddy³  Cherith N Reid⁵  Mark W Ruddock⁵  Brian Duggan¹  Ricardo de Matos Simoes³  Funso Abogunrin³  Frank Emmert-Streib³ 

[1] Department of Urology, Belfast City Hospital, 75 Lisburn Road, Belfast, BT9 7AB, Northern Ireland;Department of Pathology, Royal Victoria Hospital, 274 Grosvenor Road, Belfast, BT12 6AB, Northern Ireland;Centre for Cancer Research & Cell Biology, Queens University Belfast, 97 Lisburn Road, Belfast, BT9 7BL, Northern Ireland;Department of Pathology, Belfast City Hospital, 75 Lisburn Road, Belfast, BT9 7AB, Northern Ireland;Molecular Biology, Randox Laboratories Ltd, Diamond Road, Crumlin, BT29 4QY, Northern Ireland

关键词: proteinuria;    urothelial cancer;    feature selection;    hierarchical clustering;    Random Forests Classifier;    risk stratification;    biomarker;    hematuria;   

Others  :  857225
DOI  :  10.1186/1741-7015-11-12

 received in 2012-06-17, accepted in 2013-01-17,  发布年份 2013

【 摘 要 】

Background

Ineffective risk stratification can delay diagnosis of serious disease in patients with hematuria. We applied a systems biology approach to analyze clinical, demographic and biomarker measurements (n = 29) collected from 157 hematuric patients: 80 urothelial cancer (UC) and 77 controls with confounding pathologies.

Methods

On the basis of biomarkers, we conducted agglomerative hierarchical clustering to identify patient and biomarker clusters. We then explored the relationship between the patient clusters and clinical characteristics using Chi-square analyses. We determined classification errors and areas under the receiver operating curve of Random Forest Classifiers (RFC) for patient subpopulations using the biomarker clusters to reduce the dimensionality of the data.

Results

Agglomerative clustering identified five patient clusters and seven biomarker clusters. Final diagnoses categories were non-randomly distributed across the five patient clusters. In addition, two of the patient clusters were enriched with patients with 'low cancer-risk' characteristics. The biomarkers which contributed to the diagnostic classifiers for these two patient clusters were similar. In contrast, three of the patient clusters were significantly enriched with patients harboring 'high cancer-risk" characteristics including proteinuria, aggressive pathological stage and grade, and malignant cytology. Patients in these three clusters included controls, that is, patients with other serious disease and patients with cancers other than UC. Biomarkers which contributed to the diagnostic classifiers for the largest 'high cancer- risk' cluster were different than those contributing to the classifiers for the 'low cancer-risk' clusters. Biomarkers which contributed to subpopulations that were split according to smoking status, gender and medication were different.

Conclusions

The systems biology approach applied in this study allowed the hematuric patients to cluster naturally on the basis of the heterogeneity within their biomarker data, into five distinct risk subpopulations. Our findings highlight an approach with the promise to unlock the potential of biomarkers. This will be especially valuable in the field of diagnostic bladder cancer where biomarkers are urgently required. Clinicians could interpret risk classification scores in the context of clinical parameters at the time of triage. This could reduce cystoscopies and enable priority diagnosis of aggressive diseases, leading to improved patient outcomes at reduced costs.

【 授权许可】

   
2013 Emmert-Streib et al; licensee BioMed Central Ltd.

【 图 表 】

【 参考文献 】

• [1]Mostafid H, Persad R, Kockelbergh R, Fawcett D: Is it time to re-design the hematuria clinic? BJU Int 2010, 105:585-588.
• [2]Jacobs BL, Lee CT, Montie JE: Bladder cancer in 2010: how far have we come? CA Cancer J Clin 2010, 60:244-272.
• [3]Jemal A, Bray F, Center MM, Ferlay J, Ward E, Forman D: Global cancer statistics. CA Cancer J Clin 2011, 61:69-90.
• [4]Kulkarni GS, Finelli A, Fleshner NE, Jewett MA, Lopushinsky SR, Alibhai SM: Optimal management of high-risk T1G3 bladder cancer: a decision analysis. PLoS Med 2007, 4:e284.
• [5]van der Aa MN, Steyerberg EW, Bangma C, van Rhijn BW, Zwarthoff EC, van der Kwast TH: Cystoscopy revisited as the gold standard for detecting bladder cancer recurrence: diagnostic review bias in the randomized, prospective CEFUB trial. J Urol 2010, 183:76-80.
• [6]Lotan Y, Elias K, Svatek RS, Bagrodia A, Nuss G, Moran B, Sagalowsky AI: Bladder cancer screening in a high risk asymptomatic population using a point of care urine based protein tumor marker. J Urol 2009, 182:52-57.
• [7]Kinders R, Jones T, Root R, Bruce C, Murchison H, Corey M, Williams L, Enfield D, Hass GM: Complement factor H or a related protein is a marker for transitional cell cancer of the bladder. Clin Cancer Res 1998, 4:2511-2520.
• [8]Johnston B, Morales A, Emerson L, Lundie M: Rapid detection of bladder cancer: a comparative study of point of care tests. J Urol 1997, 158:2098-2101.
• [9]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: The impact of biomarkers in multivariate algorithms for bladder cancer diagnosis in patients with hematuria. Cancer 2011, 118:2641-2650.
• [10]Leibovici D, Grossman HB, Dinney CP, Millikan RE, Lerner S, Wang Y, Gu J, Dong Q, Wu X: Polymorphisms in inflammation genes and bladder cancer: from initiation to recurrence, progression, and survival. J Clin Oncol 2005, 23:5746-5756.
• [11]Margel D, Pesvner-Fischer M, Baniel J, Yossepowitch O, Cohen IR: Stress proteins and cytokines are urinary biomarkers for diagnosis and staging of bladder cancer. Eur Urol 2011, 59:113-119.
• [12]Vidal M: A unifying view of 21st century systems biology. FEBS Lett 2009, 583:3891-3894.
• [13]Emmert-Streib F, Glazko GV: Network biology: a direct approach to study biological function. Wiley Interdiscip Rev Syst Biol Med 2011, 3:379-391.
• [14]Bossuyt PM, Reitsma JB, Bruns DE, Gatsonis CA, Glasziou PP, Irwig LM, Lijmer JG, Moher D, Rennie D, de Vet HC, Standards for Reporting of Diagnostic Accuracy: Towards complete and accurate reporting of studies of diagnostic accuracy: the STARD initiative. Standards for Reporting of Diagnostic Accuracy. Clin Chem 2003, 49:1-6.
• [15]Bossuyt PM, Reitsma JB, Bruns DE, Gatsonis CA, Glasziou PP, Irwig LM, Moher D, Rennie D, de Vet HC, Lijmer JG, Standards for Reporting of Diagnostic Accuracy: The STARD statement for reporting studies of diagnostic accuracy: explanation and elaboration. Clin Chem 2003, 49:7-18.
• [16]Barratt J, Topham P: Urine proteomics: the present and future of measuring urinary protein components in disease. CMAJ 2007, 177:361-368.
• [17]Fitzgerald SP, Lamont JV, McConnell RI, Benchikh el O: Development of a high-throughput automated analyzer using biochip array technology. Clin Chem 2005, 51:1165-1176.
• [18]Theodoridis S: Pattern Recognition. 2nd edition. Amsterdam; London: Academic Press; 2003.
• [19]Breiman L: Bagging predictors. Machine Learning 1996, 24:123-140.
• [20]Zhang H, Singer BH: Recursive Partitioning and Applications. New York: Springer; 2010.
• [21]Haematuria guidelines [http://www.baus.org.uk/AboutBAUS/publications/haematuria-guidelines] webcite
• [22]Fassett RG, Venuthurupalli SK, Gobe GC, Coombes JS, Cooper MA, Hoy WE: Biomarkers in chronic kidney disease: a review. Kidney Int 2011, 80:806-821.
• [23]Goldstein SL: Acute kidney injury biomarkers: renal angina and the need for a renal troponin I. BMC Med 2011, 9:135. BioMed Central Full Text
• [24]Bauer M, Eickhoff JC, Gould MN, Mundhenke C, Maass N, Friedl A: Neutrophil gelatinase-associated lipocalin (NGAL) is a predictor of poor prognosis in human primary breast cancer. Breast Cancer Res Treat 2008, 108:389-397.
• [25]Perkovic V, Verdon C, Ninomiya T, Barzi F, Cass A, Patel A, Jardine M, Gallagher M, Turnbull F, Chalmers J, Craig J, Huxley R: The relationship between proteinuria and coronary risk: a systematic review and meta-analysis. PLoS Med 2008, 5:e207.
• [26]Mason RA, Morlock EV, Karagas MR, Kelsey KT, Marsit CJ, Schned AR, Andrew AS: EGFR pathway polymorphisms and bladder cancer susceptibility and prognosis. Carcinogenesis 2009, 30:1155-1160.
• [27]McShane LM: Statistical challenges in the development and evaluation of marker-based clinical tests. BMC Medicine 2012, 10:52. BioMed Central Full Text
• [28]Marchio C, Dowsett M, Reis-Filho JS: Revisiting the technical validation of tumour biomarker assays: how to open a Pandora's box. BMC Medicine 2011, 9:41. BioMed Central Full Text
• [29]Ferrante di Ruffano L, Hyde CJ, McCaffery KJ, Bossuyt PM, Deeks JJ: Assessing the value of diagnostic tests: a framework for designing and evaluating trials. BMJ 2012, 344:e686.
• [30]Liu ET: Systems Biomedicine. Boston: Academic Press; 2010.