Performance Comparison of Screening Tests for POAG for T2DM Using Comp2ROC Package

  • Ana C. Braga
  • Lígia Figueiredo
  • Dália Meira
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8581)


Primary open angle glaucoma (POAG) is a leading cause of blindness [8]. The commonly accepted risk factors for POAG include older age, high intraocular pressure, positive family history of glaucoma, and race [3].

Individuals with type 2 diabetes mellitus (T2DM) are at greater risk of having open-angle glaucoma (POAG) than those without T2DM. Thus, screening programs for diabetic retinopathy may be an excellent opportunity for screening for POAG and implementation of additional tests.

In this work we intend to evaluate the performance of GDx measures for detecting POAG through the methodology of ROC curves.

One retrospective cross-sectional study was carried out on individuals with T2DM with evaluation of diabetic retinopathy from 2008 to 2010 in Hospital Centre of Vila Nova de Gaia Northern Portugal. Individuals who had a positive screen were referred for scanning the nerve fiber layer of the retina with GDxTMdevice. In this study, the diagnosis of POAG was based on a computerized ophthalmoscopy and static analysis and based on this, the eyes were classified as healthy (n N  = 85) and with definite glaucoma (n A  = 37).

The comparison of diagnostic indicators was performed by Comp2ROC package [2].


ROC (Receiver Operating Characteristic) AUC (Area Under the Curve) Comp2ROC 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Braga, A.C., Costa, L., Oliveira, P.: An alternative method for global and partial comparison of two diagnostic system based on ROC curves. Journal of Statistical Computation and Simulation 83(2), 307–325 (2013)CrossRefMathSciNetzbMATHGoogle Scholar
  2. 2.
    Braga, A.C., Frade, H.: Comp2ROC: R Package to Compare Two ROC Curves. In: Mohamad, M.S., Nanni, L., Rocha, M.P., Fdez-Riverola, F. (eds.) 7th International Conference on Practical Applications of Computational Biology & Bioinformatics (PACBB 2013). AISC, vol. 222, pp. 127–136. Springer, Switzerland (2013)Google Scholar
  3. 3.
    Chopra, V., Varma, R., Francis, B.A., Wu, J., Torres, M., Azen, S.P.: Type 2 diabetes mellitus and the risk of open-angle glaucoma the Los Angeles Latino Eye Study. Ophthalmology 115(2), 227–232 (2008)CrossRefGoogle Scholar
  4. 4.
    DeLong, E., DeLong, D., Clarkepearson, D.: Comparing the areas under 2 or more correlated receiver operating characteristic curves - a non parametrical approach. Biometrics 44(3), 837–845 (1988)CrossRefzbMATHGoogle Scholar
  5. 5.
    Dodd, L.E., Pepe, M.S.: Partial AUC estimation and regression. Biometrics 59(3), 614–623 (2003)CrossRefMathSciNetzbMATHGoogle Scholar
  6. 6.
    Hanley, J., McNeil, B.: A method of comparing the areas under receiver operating characteristic curves derived from the same cases. Radiology 148(3), 839–843 (1983)Google Scholar
  7. 7.
    Jiang, Y.L., Metz, C.E., Nishikawa, R.M.: A receiver operating: Characteristic partial area index for highly sensitive diagnostic tests. Radiology 201(3), 745–750 (1996)Google Scholar
  8. 8.
    Leske, M.C.: The epidemiology of open-angle glaucoma: A review. Am. J. Epidemiol. 118(2), 166–191 (1983)Google Scholar
  9. 9.
    Weinreb, R.N., Khaw, P.T.: Primary open-angle glaucoma. Lancet 363, 1711–1720 (2004)CrossRefGoogle Scholar
  10. 10.
    Metz, C.E.: Statistical Analysis of ROC Dara in Evaluating Diagnostic Performance. In: Proceeding of First Midyear Topical Symposium: Multiple Regression Analysis Application in the Health Science, vol. 13, pp. 365–384 (1986)Google Scholar
  11. 11.
    Metz, C.E., Wang, P.-L., Kronman, H.: A new approach for testing the significance of differences between ROC curves measured from correlated data. In: Proceedings of the 8th Conference in Information Processing in Medical Imaging, Brussels, pp. 432–445 (1983)Google Scholar
  12. 12.
    McClish, D.K.: Analyzing a portion of the ROC curve. Med. Decis. Making 9(3), 190–195 (1989)CrossRefGoogle Scholar
  13. 13.
    Pepe, M.S.: The Statistical Evaluation of Medical Tests for Classification an Prediction. Oxford Statistical Science Series. Oxford University Press, New York (2003)Google Scholar
  14. 14.
    R Development Core Team. R: A language and environment for statistical computing. Vienna: R Foundation for Statistical Computing (2006),
  15. 15.
    Rockette, H.E., Obuchowski, N.A., Gur, D.: Nonparametric estimation of degenerate ROC data sets used for comparison of imaging-systems. Invest. Radiol. 25(7), 835–837 (1990)CrossRefGoogle Scholar
  16. 16.
    Swets, J.A., Pickett, R.M.: Evaluation of Diagnostic Systems Methods from Signal Detection Theory. Academic Press, London (1982)Google Scholar
  17. 17.
    Thompson, M.L., Zucchini, W.: On the statistical analysis of ROC curves. Stat. Med. 8(10), 1277–1290 (1989)CrossRefGoogle Scholar
  18. 18.
    Wieand, S., Gail, M.H., James, B.R., James, K.L.: A family of nonparametric statistics for comparing diagnostic markers with paired or unpaired data. Biometrika 76(3), 585–592 (1989)CrossRefMathSciNetzbMATHGoogle Scholar
  19. 19.
    Zhang, D., Zhou, X., Freeman, D., Freeman, J.: A nonparametric method for the comparison of partial areas under ROC curves and its application to large health care data sets. Stat. Med. 21(5), 701–715 (2002)CrossRefGoogle Scholar
  20. 20.
  21. 21.
    Sharma, A., Sobti, A., Wadhwani, M., Panda, A.: Evaluation of Retinal Nerve Fiber Layer using Scanning Laser Polarimetry,

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Ana C. Braga
    • 1
  • Lígia Figueiredo
    • 2
  • Dália Meira
    • 2
  1. 1.Department of Production and Systems Engineering,Algoritmi Research CentreUniversity of MinhoBragaPortugal
  2. 2.Department of OphthalmologyCentro Hospitalar de Vila Nova de Gaia/Espinho EPEVila Nova de GaiaPortugal

Personalised recommendations