Machine Learning Methods in the Comparative Evaluation of Various Approaches to the Surgical Treatment of Primary Angle Closure

Purpose. To evaluate the application of the principal component analysis (PCA) and DD-SIMCA in a comparative analysis of the surgical treatment of primary angle closure.

Material and methods. The prospective study included 90 patients. Group 1 — 30 patients with primary angle closure (PAC) with planned laser peripheral iridotomy (LPI). Group 2 — 30 patients with PAC, with planned phacoemulsification with intraocular lens implantation (PE+IOL). Group 3 — 30 eyes without ophthalmic pathology. All subjects underwent SS-OCT. Thirty-seven parameters were analyzed, including intraocular pressure, choroidal thickness in the macula, anterior chamber depth, lens vault, iris curvature and thickness, angle opening distance, and iridotrabecular space at 500 µm and 750 µm from the scleral spur. Since all these parameters correlate with each other, machine learning methods were used: PCA and the DD-SIMCA one-class classification method. For this purpose graphs of scores and loads in the PCA model for groups 1 and 2 were plotted. In the score plot, patients with PAC with average and extreme eye parameters were identified, and in the loading plot, relationships between the parameters of patients with PM were used to analyze correlations in the future. In the DD-SIMCA method, group 1 is taken as representatives of the target class.

Results. A classification model based on 2 principal components with a given type I error α = 0.01 demonstrated a sensitivity of 100 % for patients in its own group and a sensitivity of 93 % for patients in group 2. These results confirm similarity of group 1 and group 2. The specificity for the control group was 100 %, and this group located far from the target group.

Conclusion. Machine learning methods make it possible to compare groups with multivariate and correlated parameters. PCA allows the identification of patients with extreme parameters and the evaluation of correlations between multiple parameters. DDSIMCA confirms the validity of comparing the results of treatment with LPI and FE + IOL. 

1. Quigley H.A. Long-term follow-up of laser iridotomy. Ophthalmology. 1981;88(3):218–224. DOI: 10.1016/s0161-6420(81)35038-6

2. Sihota R., Rishi K., Srinivasan G., Gupta V., Dada T., Singh K. Functional evaluation of an iridotomy in primary angle closure eyes. Graefe’s Arch Clin Exp Ophthalmol = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie. 2016;254(6):1141–1149. DOI: 10.1007/s00417-016-3298-x

3. Kurysheva N.I., Sharova G.A. Role of Selective Laser Trabeculoplasty in the Treatment of Primary Angle Closure of the Anterior Chamber. Effective Pharmacotherapy = Effektivnaya farmakoterapiya. 2022;18(11):22–28 (In Russ.). DOI: 10.33978/2307-3586-2022-18-11-22-28

4. Kurysheva N.I., Sharova G.A. Comparative study of retinal microcirculation in primary angle closure disease and early primary open-angle glaucoma. Annals of Ophthalmology = Vestnik oftal’mologii. 2022;138(1):44–51 (In Russ.). DOI: 10.17116/oftalma202213801144

5. Kurysheva N.I., Sharova G.A. Efficacy of laser iridotomy in primary angle closure suspects and primary angle closure glaucoma. Eye = Glaz 2022;24(1):20–33 (In Russ.). DOI: 10.33791/2222-4408-2022-1-20-33

6. Song M.K., Sung K.R., Shin J.W., Jo Y.H., Won H.J. Glaucomatous Progression After Lens Extraction in Primary Angle Closure Disease Spectrum. J Glaucoma. 2020;29(8):711–717. DOI: 10.1097/IJG.0000000000001537

7. Song,M.K., Shin J.W., Sung, K.R. Factors Associated with Deterioration of Primary Angle Closure after Lens Extraction. J.Clin. Med. 2022;11:2557. DOI: 10.3390/jcm11092557

8. Azuara-Blanco A., Burr J., Ramsay C., Cooper D. Effectiveness of early lens extraction for the treatment of primary angle-closure glaucoma (EAGLE): a andomized controlled trial. Lancet. 2016;388(10052):1389–1397. DOI: 10.1016/S0140-6736(16)30956-4

9. Rodionova O.Ye, Pomerantsev A.L. Chemometrics: achievements and prospects. Russian Chemical Reviews = Uspehi himii. 2006;75(4):302–317 (In Russ.). DOI: 10.1070/RC2006v075n04ABEH003599

10. Pomerantsev A.L. Acceptance areas for multivariate classification derived by projection methods. J. Chemometrics. 2008;22:601–609. DOI: 10.1002/cem.1147

11. Shehab M., Abualigah L., Shambour Q. Machine learning in medical applications: A review of state-of-the-art methods [published online ahead of print, 2022 Mar 28]. Comput Biol Med. 2022;145:105458. DOI: 10.1016/j.compbiomed.2022.10

12. Busnatu Ș., Niculescu A.G., Bolocan A. Clinical Applications of Artificial Intelligence-An Updated Overview. J Clin Med. 2022;11(8):2265. DOI: 10.3390/jcm11082265

13. Shah S.M., Khan R.A., Arif S., Sajid U. Artificial intelligence for breast cancer analysis: Trends & directions. Comput Biol Med. 2022;142:105221. DOI: 10.1016/j.compbiomed.2022.105221

14. Nuzzi R., Boscia G., Marolo P., Ricardi F. The Impact of Artificial Intelligence and Deep Learning in Eye Diseases: A Review. Front Med (Lausanne). 2021;8:710329. DOI: 10.3389/fmed.2021.710329

15. Asaoka R., Murata H., Hirasawa K. Using Deep Learning and Transfer Learning to Accurately Diagnose Early-Onset Glaucoma From Macular Optical Coherence Tomography Images. Am J Ophthalmol. 2019;198:136–145. DOI: 10.1016/j.ajo.2018.10.007

16. Shibata N., Tanito M., Mitsuhashi K. Development of a deep residual learning algorithm to screen for glaucoma from fundus photography. Sci Rep. 2018;8(1):14665. DOI: 10.1038/s41598-018-33013-w

17. Hood D.C., De Moraes C.G. Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs. Ophthalmology. 2018;125(8):1207–1208. DOI: 10.1016/j.ophtha.2018.04.020

18. Asaoka R., Murata H., Iwase A., Araie M. Detecting Preperimetric Glaucoma with Standard Automated Perimetry Using a Deep Learning Classifier. Ophthalmology. 2016;123(9):1974–1980. DOI: 10.1016/j.ophtha.2016.05.029

19. Wang Y., Cun Q., Li J. Prevalence, ethnic differences and risk factors of primary angle-closure glaucoma in a multiethnic Chinese adult population: the Yunnan Minority Eye Study [published online ahead of print, 2021 Dec 21]. Br J Ophthalmol. 2021;bjophthalmol-2021-320241. DOI: 10.1136/bjophthalmol-2021-320241

20. Quinn B., McCarron P., Hong Y. Elementomics combined with dd-SIMCA and K-NN to identify the geographical origin of rice samples from China, India, and Vietnam. Food Chem. 2022;386:132738. DOI: 10.1016/j.foodchem.2022.132738

21. Pinto F.G., Mahmud I., Rubio V.Y. Data-Driven Soft Independent Modeling of Class Analogy in Paper Spray Ionization Mass Spectrometry-Based Metabolomics for Rapid Detection of Prostate Cancer. Anal Chem. 2022;94(4):1925–1931. DOI: 10.1021/acs.analchem.1c04004

22. Ferreira R., Marcos A.S., Anjos M., Maia C., Pinto A.R.G., de Azevedo A., de Brito J. Long-term analysis of the physical properties of the mixed recycled aggregate and their effect on the properties of mortars. Construction and Building Materials. 2021;274:121796. DOI: 10.1016/j.conbuildmat.2020.121796

23. Nazarenko R.V., Irzhak A.V., Pomerantsev A.L., Rodionova O.Y. Confocal Raman spectroscopy and multivariate data analysis for evaluation of spermatozoa with normal and abnormal morphology. A feasibility study. Chemom. Intell. Lab. Syst. 2018;182(October):172–179. DOI: 10.1016/j.chemolab.2018.10.002

24. Belyaev I., Marolda A., Praetorius J.-P., Sarkar A., Medyukhina A., Hünniger K., Kurzai O., Thilo Figge M. Automated Characterisation of Neutrophil Activation Phenotypes in Ex Vivo Human Candida Blood Infections. Computational and Structural Biotechnology Journal. 2022;10;20:2297-2308. DOI: 10.1016/j.csbj.2022.05.007

25. Foster P.J., Buhrmann R., Quigley H.A., Johnson G.J. The definition and classification of glaucoma in prevalence surveys. Br J Ophthalmol. 2002;86(2):238–242. DOI: 10.1136/bjo.86.2.238

26. Chylack L.T. Jr, Wolfe J.K., Singer D.M. The Lens Opacities Classification System III. The Longitudinal Study of Cataract Study Group. Arch Ophthalmol. 1993;111(6):831–836. DOI: 10.1001/archopht.1993.01090060119035

27. Kurysheva N.I., Sharova G.A. The Role of Optical Coherence Tomography in the Diagnosis of Angle Closed Diseases of the Anterior Chamber. Part 1: Visualization of the Anterior Segment of the Eye. Ophthalmology in Russia = Oftal’mologiya. 2021;18(2):208–215 (In Russ.). DOI: 10.18008/1816-5095-2021-2-208-215

28. Kurysheva N.I., Boyarinceva M.A., Fomin A.V. Choroidal thickness in primary angle-closure glaucoma: the results of Measurement by Means of Optical Coherence Tomography. Ophthalmology in Russia = Oftal’mologiya.. 2013;10(4):26–31. DOI: 10.18008/1816-5095-2013-4-26-31

29. He M., Jiang Y., Huang S., Chang D.S., Munoz B., Aung T., Foster P.J., Friedman D.S. Laser peripheral iridotomy for the prevention of angle closure: a single-centre, Randomized controlled trial. Lancet. 2019 Apr 20;393(10181):1609–1618. DOI: 10.1016/S0140-6736(18)32607-2

30. Pomerantsev A.L., Rodionova O.Ye. Concept and role of extreme objects in PCA/ SIMCA. J. Chemometrics. 2014;28:429–438. DOI: 10.1002/cem.2506 31. Pomerantsev A.L., Rodionova O.Ye. On the type II error in SIMCA method. J. Chemometrics. 2014;28:518-522. DOI: 10.1002/cem.2610

31. Shchuko A.G., Chesheyko Ye.Yu., Yuryeva T.N. Criteria for differential diagnostics of functional angular block — latent stage of closed — angle glaucoma. Annals of Orenburg State University = Vestnik Orenburgskogo gosudarstvennogo universiteta. 2012;148(12):239–243 (In Russ.).

32. Schuko A.G., Chesheiko E.Yu., Yur’eva T.N., Malyshev V.V. Structural and functional changes of visual system in patients with functional angular block. Russian Medical Journal. Clinical Ophthalmology = Rossiyskiy medicinskiy zhurnal. Klinicheskaya oftal’mologiya. 2007;8(4);137 (In Russ.).

33. Bo J., Changulani T., Cheng M.L., Tatham A.J. Outcome Following Laser Peripheral Iridotomy and Predictors of Future Lens Extraction. J Glaucoma. 2018;27(3):275– 280. DOI: 10.1097/IJG.0000000000000863

34. Huang G., Gonzalez E., Peng P.H. Anterior chamber depth, iridocorneal angle width, and intraocular pressure changes after phacoemulsification: narrow vs open iridocorneal angles [published correction appears in Arch Ophthalmol. 2011 Nov;129(11):1497]. Arch Ophthalmol. 2011;129(10):1283-1290. DOI: 10.1001/archophthalmol.2011.272

35. Zebardast N., Kavitha S., Krishnamurthy P. Changes in Anterior Segment Morphology and Predictors of Angle Widening after Laser Iridotomy in South Indian Eyes. Ophthalmology. 2016;123(12):2519–2526. DOI: 10.1016/j.ophtha.2016.08.020

36. Moghimi S., Chen R., Johari M., Bijani F., Mohammadi M., Khodabandeh A., He M.G., Lin S.C. Changes in anterior segment morphology after laser peripheral iridotomy in acute primary angle closure. Am J Ophthalmol. 2016;166:133–140. DOI: 10.1016/j.ajo.2016.03.032

37. Huang G., Gonzalez E., Lee R., Osmonavic S., Leeungurasatien T., He M., Lin S.C. Anatomic predictors for anterior chamber angle opening after laser peripheral iridotomy in narrow angle eyes. Curr Eye Res. 2012;37(7):575–582. DOI: 10.3109/02713683.2012.655396

38. Chen X., Wang X., Tang Y., Sun X., Chen Y. Optical coherence tomography analysis of anterior segment parameters before and after laser peripheral iridotomy in primary angle-closure suspects by using CASIA2. BMC Ophthalmol. 2022;22(1):144. DOI: 10.1186/s12886-022-02366-2

39. Shams P.N., Foster P.J. Clinical outcomes after lens extraction for visually significant cataract in eyes with primary angle closure. J Glaucoma. 2012;21(8):545–550. DOI: 10.1097/IJG.0b013e31821db1db