Abstract
This study is to propose and evaluate the diagnostic accuracy of decision tree classifiers using the full set of standard GDx VCC measurements for classifying glaucoma in a Taiwan Chinese population. The classifiers were trained and tested using standard GDx VCC parameters from examinations of 74 subjects with glaucoma and 72 normal subjects. Six promising decision rules were generated from decision tree methods and the overall accuracy from tenfold cross validation was 0.801. Classification tree based on GDx VCC data promises to be a diagnostic tool in glaucoma disease. However, its exact clinical application in glaucoma practice should be retested. Further longitudinal study should address this issue.
Similar content being viewed by others
References
Weinreb, R. N., Dreher, A. W., Coleman, A., et al., Histopathologic validation of Fourier-ellipsometry measurements of retinal nerve fiber layer thickness. Arch. Ophthalmol. 108:557–560, 1990.
Weinreb, R. N., Bowd, C., and Zangwill, L. M., Scanning laser polarimetry in monkey eyes using variable corneal polarization compensation. J. Glaucoma. 11:378–384, 2002.
Huang, X. R., and Knighton, R. W., Linear birefringence of the retinal nerve fiber layer measured in vitro with a multispectral imaging micropolarimeter. J. Biomed. Opt. 7:199–204, 2002.
Dreher, A. W., and Bailey, E. D., Assessment of the retinal nerve fiber layer by scanning-laser polarimetry. In: Parel, J.-M. A., and Ren, Q. (Eds.), Proceedings of SPIE: Ophthalmic Technologies III, Vol. 1877SPIE, Bellingham, WA, pp. 266–271, 1993.
Cense, B., Chen, T. C., Park, B. H., et al., Thickness and birefringence of healthy retinal nerve fiber layer tissue measured with polarization-sensitive optical coherence tomography. Invest. Ophthalmol. Vis. Sci. 45:2606–2612, 2004.
Vermeer, K. A., Reus, N. J., Vos, F. M., et al., Automated detection of wedge-shaped defects in polarimetric images of the retinal nerve fibre layer. Eye. 20:776–784, 2006.
Garway-Heath, D. F., Greaney, M. J., and Caprioli, J., Correction for the erroneous compensation of anterior segment birefringence with the scanning laser polarimeter for glaucoma diagnosis. Invest. Ophthalmol. Vis. Sci. 43:1465–1474, 2002.
Zhou, Q., and Weinreb, R. N., Individualized compensation of anterior segment birefringence during scanning laser polarimetry. Invest. Ophthalmol. Vis. Sci. 43:2221–2228, 2002.
Bowd, C., Medeiros, F. A., Zhang, Z., et al., Relevance vector machine and support vector machine classifier analysis of scanning laser polarimetry retinal nerve fiber layer measurements. Invest. Ophthalmol. Vis. Sci. 46:1322–1329, 2005.
Weinreb, R. N., Bowd, C., and Zangwill, L. M., Glaucoma detection using scanning laser polarimetry with variable corneal polarization compensation. Arch. Ophthalmol. 121:218–224, 2003.
Reus, N. J., and Lemij, H. G., Diagnostic accuracy of the GDx VCC for glaucoma. Ophthalmology. 111:1860–1865, 2004.
Medeiros, F. A., Zangwill, L. M., Bowd, C., et al., Comparison of the GDx VCC scanning laser polarimeter, HRT II confocal scanning laser ophthalmoscope, and stratus OCT optical coherence tomograph for the detection of glaucoma. Arch. Ophthalmol. 122:827–837, 2004.
Leung, C. K., Chan, W. M., Chong, K. K., et al., Comparative study of retinal nerve fiber layer measurement by StratusOCT and GDx VCC, I: correlation analysis in glaucoma. Invest. Ophthalmol. Vis. Sci. 46:3214–3220, 2005.
Da Pozzo, S., Fuser, M., Vattovani, O., et al., GDx-VCC performance in discriminating normal from glaucomatous eyes with early visual field loss. Graefes. Arch. Clin. Exp. Ophthalmol. 244:689–695, 2006.
Jonas, J. B., Budde, W. M., and Panda-Jonas, S., Ophthalmoscopic evaluation of the optic nerve head. Surv. Ophthalmol. 43:293–320, 1999.
Keltner, J. L., Johnson, C. A., Cello, K. E., et al., Classification of visual field abnormalities in the ocular hypertension treatment study. Arch. Ophthalmol. 121:643–650, 2003.
Caprioli, J., Park, H. J., Ugurlu, S., et al., Slope of the peripapillary nerve fiber layer surface in glaucoma. Invest. Ophthalmol. Vis. Sci. 39:2321–2328, 1998.
DeLong, E. R., DeLong, D. M., and Clarke-Pearson, D. L., Comparing the areas under two of more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics. 44:837–845, 1988.
Hanley, J. A., and McNeil, B. J., A method of comparing the areas under receiver operating characteristic curves derived from the same cases. Radiology. 148:839–843, 1983.
Chen, H. Y., Huang, M. L., Tsai, Y. Y., et al., Diagnostic value of GDx polarimetry in Taiwan Chinese population. Optom. Vis. Sci. 84:640–646, 2007.
Jonas, J. B., Mardin, C. Y., Schlotzer-Schrehardt, U., et al., Morphometry of the human lamina cribrosa surface. Invest. Ophthalmol. Vis. Sci. 32:401–405, 1991.
Quigley, H. A., and Addicks, E. M., Regional differences in the structure of the lamina cribrosa and their relation to glaucomatous optic nerve damage. Arch. Ophthalmol. 99:137–143, 1981.
Abu-Hanna, A., and Lucas, P. J., Prognostic models in medicine. AI and statistical approaches. Methods Inf. Med. 40:1–5, 2001.
de Rooij, A., et al., Identification of high-risk subgroups in very elderly intensive care unit patients. Crit. Care. 11:R33, 2007.
Abu-Hanna, A., and de Keizer, N., Integrating classification trees with local logistic regression in intensive care prognosis. Artif. Intell. Med. 29:5–23, 2003.
Huang, M. L., Chen, H. Y., and Lin, J. C., Rule extraction for glaucoma detection with summary data from Stratus OCT. Invest. Ophthalmol. Vis. Sci. 48:244–250, 2007.
Hothorn, T., and Lausen, B., Bagging tree classifiers for laser scanning images: A data- and simulation-based strategy. Artif. Intell. Med. 27:65–79, 2003.
Naithani, P., Sihota, R., Sony, P., et al., Evaluation of optical coherence tomography and Heidelberg retinal tomography parameters in detecting early and moderate glaucoma. Invest. Ophthalmol. Vis. Sci. 48:3138–3145, 2007.
Garway-Heath, D. F., and Hitchings, R. A., Sources of bias in studies of optic disc and retinal nerve fiber morphology. Br. J. Ophthalmol. 82:986, 1988.
Medeiros, F. A., Ng, D., Zangwill, L. M., Sample, P. A., et al., The effects of study design and spectrum bias on the evaluation of diagnostic accuracy of confocal scanning laser ophthalmoscopy in glaucoma. Invest. Ophthalmol. Vis. Sci. 48:214–222, 2007.
Weinreb, R. N., and Meideros, F. A., Is scanning laser polarimetry ready for clinical practice? Am. J. Ophthalmol. 143:674–676, 2007.
Lemij, H. G., The value of polarimetry in the evaluation of the optic nerve in glaucoma. Curr. Opin. Ophthalmol . 12:138–142, 2001.
Blumenthal, E. Z., Parikh, R. S., Pe'er, J., et al., Retinal nerve fibre layer imaging compared with histological measurements in a human eye. Eye. 23:171–175, 2009.
Acknowledgments
The authors would like to thank for the financial support under contract no. NSC-97-2628-E-167-001-MY3 and DMR-97-079.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Huang, ML., Chen, HY. Glaucoma Classification Model Based on GDx VCC Measured Parameters by Decision Tree. J Med Syst 34, 1141–1147 (2010). https://doi.org/10.1007/s10916-009-9333-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10916-009-9333-2