Validating the Usefulness of the “Random Forests” Classifier to Diagnose Early Glaucoma With Optical Coherence Tomography

American Journal of Ophthalmology

Volumn 174, Issue , 2017, Pages 95-103

  Asaoka, Ryo ^a   Hirasawa, Kazunori ^b   Iwase, Aiko ^c   Fujino, Yuri ^a   Murata, Hiroshi ^a   Shoji, Nobuyuki ^b   Araie, Makoto ^d  

^a UNIVERSITY OF TOKYO   (Japan)

^b KITASATO UNIVERSITY   (Japan)

^c Tajimi Iwase Eye Clinic   (Japan)

^d Mutual Aid Association of Public School Teachers   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ADULT; ALGORITHM; ARTICLE; CLASSIFIER; CONTROLLED STUDY; CROSS-SECTIONAL STUDY; DIAGNOSTIC ACCURACY; DIAGNOSTIC TEST ACCURACY STUDY; EARLY DIAGNOSIS; FEMALE; HUMAN; INSTITUTIONAL CARE; MAJOR CLINICAL STUDY; MALE; MIDDLE AGED; OPEN ANGLE GLAUCOMA; OPTICAL COHERENCE TOMOGRAPHY DEVICE; PRIORITY JOURNAL; RANDOM FOREST; RECEIVER OPERATING CHARACTERISTIC; SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHY; VALIDATION PROCESS; CLASSIFICATION; CLINICAL TRIAL; COMPARATIVE STUDY; DIAGNOSTIC IMAGING; FOLLOW UP; GLAUCOMA, OPEN-ANGLE; GONIOSCOPY; INTRAOCULAR PRESSURE; MULTICENTER STUDY; NERVE FIBER; OPTIC DISK; OPTICAL COHERENCE TOMOGRAPHY; PATHOLOGY; PATHOPHYSIOLOGY; PHYSIOLOGY; PROCEDURES; VALIDATION STUDY; VISUAL FIELD;

CROSS-SECTIONAL STUDIES; EARLY DIAGNOSIS; FEMALE; FOLLOW-UP STUDIES; GLAUCOMA, OPEN-ANGLE; GONIOSCOPY; HUMANS; INTRAOCULAR PRESSURE; MALE; MIDDLE AGED; NERVE FIBERS; OPTIC DISK; ROC CURVE; TOMOGRAPHY, OPTICAL COHERENCE; VISUAL FIELDS;

EID: 85002156915     PISSN: 00029394     EISSN: 18791891     Source Type: Journal    
DOI: 10.1016/j.ajo.2016.11.001     Document Type: Article

References (65)

1. 1 Sommer, A., Pollack, I., Maumenee, A.E., Optic disc parameters and onset of glaucomatous field loss. I. Methods and progressive changes in disc morphology. Arch Ophthalmol 97:8 (1979), 1444–1448.
2. 2 Pederson, J.E., Anderson, D.R., The mode of progressive disc cupping in ocular hypertension and glaucoma. Arch Ophthalmol 98:3 (1980), 490–495.
3. 3 Quigley, H.A., Katz, J., Derick, R.J., et al. An evaluation of optic disc and nerve fiber layer examinations in monitoring progression of early glaucoma damage. Ophthalmology 99:1 (1992), 19–28.
4. 4 Sommer, A., Miller, N.R., Pollack, I., et al. The nerve fiber layer in the diagnosis of glaucoma. Arch Ophthalmol 95:12 (1977), 2149–2156.
5. 5 Sommer, A., Katz, J., Quigley, H.A., et al. Clinically detectable nerve fiber atrophy precedes the onset of glaucomatous field loss. Arch Ophthalmol 109:1 (1991), 77–83.
6. 6 Sommer, A., Quigley, H.A., Robin, A.L., et al. Evaluation of nerve fiber layer assessment. Arch Ophthalmol 102:12 (1984), 1766–1771.
7. 7 Kerrigan-Baumrind, L.A., Quigley, H.A., Pease, M.E., et al. Number of ganglion cells in glaucoma eyes compared with threshold visual field tests in the same persons. Invest Ophthalmol Vis Sci 41:3 (2000), 741–748.
8. 8 Harwerth, R.S., Carter-Dawson, L., Shen, F., et al. Ganglion cell losses underlying visual field defects from experimental glaucoma. Invest Ophthalmol Vis Sci 40:10 (1999), 2242–2250.
9. 9 Harwerth, R.S., Carter-Dawson, L., Smith, E.L. 3rd, et al. Neural losses correlated with visual losses in clinical perimetry. Invest Ophthalmol Vis Sci 45:9 (2004), 3152–3160.
10. 10 Quigley, H.A., Dunkelberger, G.R., Green, W.R., Retinal ganglion cell atrophy correlated with automated perimetry in human eyes with glaucoma. Am J Ophthalmol 107:5 (1989), 453–464.
11. 11 Tan, O., Chopra, V., Lu, A.T., et al. Detection of macular ganglion cell loss in glaucoma by Fourier-domain optical coherence tomography. Ophthalmology, 116(12), 2009 2305–2314.e2301-2302.
12. 12 Garas, A., Vargha, P., Hollo, G., Diagnostic accuracy of nerve fibre layer, macular thickness and optic disc measurements made with the RTVue-100 optical coherence tomograph to detect glaucoma. Eye (Lond) 25:1 (2011), 57–65.
13. 13 Moreno, P.A., Konno, B., Lima, V.C., et al. Spectral-domain optical coherence tomography for early glaucoma assessment: analysis of macular ganglion cell complex versus peripapillary retinal nerve fiber layer. Can J Ophthalmol 46:6 (2011), 543–547.
14. 14 Rao, H.L., Babu, J.G., Addepalli, U.K., et al. Retinal nerve fiber layer and macular inner retina measurements by spectral domain optical coherence tomograph in Indian eyes with early glaucoma. Eye (Lond) 26:1 (2012), 133–139.
15. 15 Kim, N.R., Lee, E.S., Seong, G.J., et al. Structure-function relationship and diagnostic value of macular ganglion cell complex measurement using Fourier-domain OCT in glaucoma. Invest Ophthalmol Vis Sci 51:9 (2010), 4646–4651.
16. 16 Rao, H.L., Kumbar, T., Addepalli, U.K., et al. Effect of spectrum bias on the diagnostic accuracy of spectral-domain optical coherence tomography in glaucoma. Invest Ophthalmol Vis Sci 53:2 (2012), 1058–1065.
17. 17 Cho, J.W., Sung, K.R., Lee, S., et al. Relationship between visual field sensitivity and macular ganglion cell complex thickness as measured by spectral-domain optical coherence tomography. Invest Ophthalmol Vis Sci 51:12 (2010), 6401–6407.
18. 18 Schulze, A., Lamparter, J., Pfeiffer, N., et al. Diagnostic ability of retinal ganglion cell complex, retinal nerve fiber layer, and optic nerve head measurements by Fourier-domain optical coherence tomography. Graefes Arch Clin Exp Ophthalmol 249:7 (2011), 1039–1045.
19. 19 Shields, M.B., Textbook of Glaucoma. 1997, Williams & Wilkins, Baltimore.
20. 20 Zimmerman, T.J., Kooner, K.S., Clinical Pathways in Glaucoma. 2001, Thieme, NY.
21. 21 Mwanza, J.C., Warren, J.L., Budenz, D.L., et al. Combining spectral domain optical coherence tomography structural parameters for the diagnosis of glaucoma with early visual field loss. Invest Ophthalmol Vis Sci 54:13 (2013), 8393–8400.
22. 22 Burgansky-Eliash, Z., Wollstein, G., Chu, T., et al. Optical coherence tomography machine learning classifiers for glaucoma detection: a preliminary study. Invest Ophthalmol Vis Sci 46:11 (2005), 4147–4152.
23. 23 Baskaran, M., Ong, E.L., Li, J.L., et al. Classification algorithms enhance the discrimination of glaucoma from normal eyes using high-definition optical coherence tomography. Invest Ophthalmol Vis Sci 53:4 (2012), 2314–2320.
24. 24 Han, J., Kamber, M., Pei, J., Data Mining: Concepts and Techniques. Burlington. 2006, Morgan Kaufmann Publishers, MA.
25. 25 Mitchell, T.M., Machine Learning. 1997, McGraw-Hill Higher Education, NY.
26. 26 Breiman, L., Random Forests. Machine Learning 45 (2001), 5–32.
27. 27 Breiman L, Cutler A. Random Forests. Available at: http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm. Accessed November 30, 2016.
28. 28 Strobl, C., Boulesteix, A.L., Kneib, T., et al. Conditional variable importance for random forests. BMC Bioinformatics, 9, 2008, 307.
29. 29 Dietterich, T.G., Ensemble learning. The Handbook of Brain Theory and Neural Networks, 2nd ed., 2002, The MIT Press, Cambridge.
30. 30 Maroco, J., Silva, D., Rodrigues, A., et al. Data mining methods in the prediction of dementia: a real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests. BMC Res Notes, 4, 2011, 299.
31. 31 Douglas, P.K., Harris, S., Yuille, A., et al. Performance comparison of machine learning algorithms and number of independent components used in fMRI decoding of belief vs. disbelief. Neuroimage 56:2 (2011), 544–553.
32. 32 Lunetta, K.L., Hayward, L.B., Segal, J., et al. Screening large-scale association study data: exploiting interactions using random forests. BMC Genet, 5, 2004, 32.
33. 33 Segal, M.R., Cummings, M.P., Hubbard, A.E., Relating amino acid sequence to phenotype: analysis of peptide-binding data. Biometrics 57:2 (2001), 632–642.
34. 34 Rao, H.L., Zangwill, L.M., Weinreb, R.N., et al. Comparison of different spectral domain optical coherence tomography scanning areas for glaucoma diagnosis. Ophthalmology 117:9 (2010), 1692–1699 1699.e1691.
35. 35 Lisboa, R., Paranhos, A. Jr., Weinreb, R.N., et al. Comparison of different spectral domain OCT scanning protocols for diagnosing preperimetric glaucoma. Invest Ophthalmol Vis Sci 54:5 (2013), 3417–3425.
36. 36 Sugimoto, K., Murata, H., Hirasawa, H., et al. Cross-sectional study: does combining optical coherence tomography measurements using the ‘Random Forest’ decision tree classifier improve the prediction of the presence of perimetric deterioration in glaucoma suspects?. BMJ Open, 3(10), 2013, e003114.
37. 37 Yoshida, T., Iwase, A., Hirasawa, H., et al. Discriminating between glaucoma and normal eyes using optical coherence tomography and the ‘Random Forests’ classifier. PLoS One, 9(8), 2014, e106117.
38. 38 Quigley, H.A., Broman, A.T., The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol 90:3 (2006), 262–267.
39. 39 Anderson, D.R., Patella, V.M., Automated Static Perimetry. 2nd ed., 1999, Mosby, St. Louis.
40. 40 Apple, D.J., Rabb, M.F., Walsh, P.M., Congenital anomalies of the optic disc. Surv Ophthalmol 27:1 (1982), 3–41.
41. 41 Bengtsson, B., Heijl, A., False-negative responses in glaucoma perimetry: indicators of patient performance or test reliability?. Invest Ophthalmol Vis Sci 41:8 (2000), 2201–2204.
42. 42 Japkowicz, N., Evaluating Learning Algorithms: A Classification Perspective. 2011, Cambridge University Press, Cambridge (UK).
43. 43 Burnham, K.P., Anderson, D.R., Multimodel inference: understanding: AIC and BIC in model selection. Socio Meth Res 33 (2004), 261–304.
44. 44 Tibshirani, R., Regression shrinkage and selection via the lasso. J R Stat Soc Series B 58:1 (1996), 267–288.
45. 45 Friedman, J., Hastie, T., Tibshirani, R., Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33:1 (2010), 1–22.
46. 46 Yuki, K., Asaoka, R., Tsubota, K., The relationship between central visual field damage and motor vehicle collisions in primary open-angle glaucoma patients. PLoS One, 9(12), 2014, e115572.
47. 47 Asaoka, D., Nagahara, A., Hojo, M., et al. The relationship between H. pylori infection and osteoporosis in Japan. Gastroenterol Res Pract, 2014, 2014, 340765.
48. 48 Asaoka, R., Measuring visual field progression in the central 10 degrees using additional information from central 24 degrees visual fields and ‘lasso regression’. PLoS One, 8(8), 2013, e72199.
49. 49 Fujino, Y., Murata, H., Mayama, C., et al. Applying “lasso” regression to predict future visual field progression in glaucoma patients. Invest Ophthalmol Vis Sci 56:4 (2015), 2334–2339.
50. 50 Demšar, J., Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7 (2006), 1–30.
51. 51 DeLong, E.R., DeLong, D.M., Clarke-Pearson, D.L., Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:3 (1988), 837–845.
52. 52 Holm, S., A simple sequentially rejective multiple test procedure. Scand J Stat 6 (1979), 65–70.
53. 53 Aickin, M., Gensler, H., Adjusting for multiple testing when reporting research results: the Bonferroni vs Holm methods. Am J Public Health 86:5 (1996), 726–728.
54. 54 Youden, W.J., Index for rating diagnostic tests. Cancer 3:1 (1950), 32–35.
55. 55 Jamie, S., Matthew, J., Roberto, C., Semantic texton forests for image categorization and segmentation. Proc IEEE Conf Computer Vision and Pattern Recognition, 2008, 1–8.
56. 56 Liang, W., Yizhou, W., Debin, Z., Building emerging pattern (EP) random forest for recognition. Proc IEEE Conf on Image Processing, 2010, 1457–1460.
57. 57 Mitchell, P., Hourihan, F., Sandbach, J., et al. The relationship between glaucoma and myopia: the Blue Mountains Eye Study. Ophthalmology 106:10 (1999), 2010–2015.
58. 58 Suzuki, Y., Iwase, A., Araie, M., et al. Risk factors for open-angle glaucoma in a Japanese population: the Tajimi Study. Ophthalmology 113:9 (2006), 1613–1617.
59. 59 Xu, L., Wang, Y., Wang, S., et al. High myopia and glaucoma susceptibility the Beijing Eye Study. Ophthalmology 114:2 (2007), 216–220.
60. 60 Perera, S.A., Wong, T.Y., Tay, W.T., et al. Refractive error, axial dimensions, and primary open-angle glaucoma: the Singapore Malay Eye Study. Arch Ophthalmol 128:7 (2010), 900–905.
61. 61 Liang, Y.B., Friedman, D.S., Zhou, Q., et al. Prevalence of primary open angle glaucoma in a rural adult Chinese population: the Handan eye study. Invest Ophthalmol Vis Sci 52:11 (2011), 8250–8257.
62. 62 Mayama, C., Tsutsumi, T., Saito, H., et al. Glaucoma-induced optic disc morphometric changes and glaucoma diagnostic ability of Heidelberg Retina Tomograph II in highly myopic eyes. PLoS One, 9(1), 2014, e86417.
63. 63 Yamazaki, Y., Yoshikawa, K., Kunimatsu, S., et al. Influence of myopic disc shape on the diagnostic precision of the Heidelberg Retina Tomograph. Jpn J Ophthalmol 43:5 (1999), 392–397.
64. 64 Shoji, T., Nagaoka, Y., Sato, H., et al. Impact of high myopia on the performance of SD-OCT parameters to detect glaucoma. Graefes Arch Clin Exp Ophthalmol 250:12 (2012), 1843–1849.
65. 65 Kim, N.R., Lee, E.S., Seong, G.J., et al. Comparing the ganglion cell complex and retinal nerve fibre layer measurements by Fourier domain OCT to detect glaucoma in high myopia. Br J Ophthalmol 95:8 (2011), 1115–1121.