54
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A holistic comparative analysis of diagnostic tests for urothelial carcinoma: a study of Cxbladder Detect, UroVysion® FISH, NMP22® and cytology based on imputation of multiple datasets

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background

          Comparing the relative utility of diagnostic tests is challenging when available datasets are small, partial or incomplete. The analytical leverage associated with a large sample size can be gained by integrating several small datasets to enable effective and accurate across-dataset comparisons. Accordingly, we propose a methodology for a holistic comparative analysis and ranking of cancer diagnostic tests through dataset integration and imputation of missing values, using urothelial carcinoma (UC) as a case study.

          Methods

          Five datasets comprising samples from 939 subjects, including 89 with UC, where up to four diagnostic tests (cytology, NMP22®, UroVysion® Fluorescence In-Situ Hybridization (FISH) and Cxbladder Detect) were integrated into a single dataset containing all measured records and missing values. The tests were firstly ranked using three criteria: sensitivity, specificity and a standard variable (feature) ranking method popularly known as signal-to-noise ratio (SNR) index derived from the mean values for all subjects clinically known to have UC versus healthy subjects. Secondly, step-wise unsupervised and supervised imputation (the latter accounting for the ‘clinical truth’ as determined by cystoscopy) was performed using personalized modelling, k-nearest-neighbour methods, multiple logistic regression and multilayer perceptron neural networks. All imputation models were cross-validated by comparing their post-imputation predictive accuracy for UC with their pre-imputation accuracy. Finally, the post-imputation tests were re-ranked using the same three criteria.

          Results

          In both measured and imputed data sets, Cxbladder Detect ranked higher for sensitivity, and urine cytology a higher specificity, when compared with other UC tests. Cxbladder Detect consistently ranked higher than FISH and all other tests when SNR analyses were performed on measured, unsupervised and supervised imputed datasets. Supervised imputation resulted in a smaller cross-validation error. Cxbladder Detect was robust to imputation showing a 2 % difference in its predictive versus clinical accuracy, outperforming FISH, NMP22 and cytology.

          Conclusion

          All data analysed, pre- and post-imputation showed that Cxbladder Detect had higher SNR and outperformed all other comparator tests, including FISH. The methodology developed and validated for comparative ranking of the diagnostic tests for detecting UC, may be further applied to other cancer diagnostic datasets across population groups and multiple datasets.

          Electronic supplementary material

          The online version of this article (doi:10.1186/s12874-015-0036-8) contains supplementary material, which is available to authorized users.

          Related collections

          Most cited references26

          • Record: found
          • Abstract: not found
          • Article: not found

          Multiple Imputation after 18+ Years

            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Genotype imputation.

            Genotype imputation is now an essential tool in the analysis of genome-wide association scans. This technique allows geneticists to accurately evaluate the evidence for association at genetic markers that are not directly genotyped. Genotype imputation is particularly useful for combining results across studies that rely on different genotyping platforms but also increases the power of individual scans. Here, we review the history and theoretical underpinnings of the technique. To illustrate performance of the approach, we summarize results from several gene mapping studies. Finally, we preview the role of genotype imputation in an era when whole genome resequencing is becoming increasingly common.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Detection of bladder cancer using a point-of-care proteomic assay.

              A combination of methods is used for diagnosis of bladder cancer because no single procedure detects all malignancies. Urine tests are frequently part of an evaluation, but have either been nonspecific for cancer or required specialized analysis at a laboratory. To investigate whether a point-of-care proteomic test that measures the nuclear matrix protein NMP22 in voided urine could enhance detection of malignancy in patients with risk factors or symptoms of bladder cancer. Twenty-three academic, private practice, and veterans' facilities in 10 states prospectively enrolled consecutive patients from September 2001 to May 2002. Participants included 1331 patients at elevated risk for bladder cancer due to factors such as history of smoking or symptoms including hematuria and dysuria. Patients at risk for malignancy of the urinary tract provided a voided urine sample for analysis of NMP22 protein and cytology prior to cystoscopy. The diagnosis of bladder cancer, based on cystoscopy with biopsy, was accepted as the reference standard. The performance of the NMP22 test was compared with voided urine cytology as an aid to cancer detection. Testing for the NMP22 tumor marker was conducted in a blinded manner. Bladder cancer was diagnosed in 79 patients. The NMP22 assay was positive in 44 of 79 patients with cancer (sensitivity, 55.7%; 95% confidence interval [CI], 44.1%-66.7%), whereas cytology test results were positive in 12 of 76 patients (sensitivity, 15.8%; 95% CI, 7.6%-24.0%). The specificity of the NMP22 assay was 85.7% (95% CI, 83.8%-87.6%) compared with 99.2% (95% CI, 98.7%-99.7%) for cytology. The proteomic marker detected 4 cancers that were not visualized during initial endoscopy, including 3 that were muscle invasive and 1 carcinoma in situ. The noninvasive point-of-care assay for elevated urinary NMP22 protein can increase the accuracy of cystoscopy, with test results available during the patient visit.
                Bookmark

                Author and article information

                Contributors
                vbreen@aut.ac.nz
                nkasabov@aut.ac.nz
                akamat@mdanderson.org
                elsie.jacobson@pacificedge.co.nz
                jimmy.suttie@pelnz.com
                paul.osullivan@pacificedge.co.nz
                laimonis.kavalieris@pacificedge.co.nz
                dave.darling@pelnz.com
                Journal
                BMC Med Res Methodol
                BMC Med Res Methodol
                BMC Medical Research Methodology
                BioMed Central (London )
                1471-2288
                12 May 2015
                12 May 2015
                2015
                : 15
                : 45
                Affiliations
                [ ]Auckland University of Technology, Auckland, New Zealand
                [ ]M. D. Anderson Cancer Center, University of Texas, Houston TX, USA
                [ ]Pacific Edge Limited, Dunedin, New Zealand
                Article
                36
                10.1186/s12874-015-0036-8
                4494166
                25962444
                fc49440b-9bf2-45cb-83ce-4b7c2d2c802b
                © Breen et al.; licensee BioMed Central. 2015

                This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.

                History
                : 3 February 2015
                : 7 May 2015
                Categories
                Research Article
                Custom metadata
                © The Author(s) 2015

                Medicine
                cancer diagnostic tests ranking,diagnostic test accuracy,multiple data integration,data imputation,urothelial carcinoma,urine cytology,nmp22,fish,cxbladder detect

                Comments

                Comment on this article