Clinical Relevance of Choroidal Thickness in Obese and Healthy Children: A Machine Learning Study

Overview

Journal Turk J Ophthalmol

Specialty Ophthalmology

Date 2023 Jun 22

PMID 37345311

Authors

Erkan Bulut

Sumeyra Koprubasi

Ozlem Dayi

Hatice Bulut

Affiliations

Soon will be listed here.

Abstract

Objectives: To analyze the effect of macular choroidal thickness (MCT) and peripapillary choroidal thickness (PPCT) on the classification of obese and healthy children by comparing the performance of the random forest (RF), support vector machine (SVM), and multilayer perceptrons (MLP) algorithms.

Materials And Methods: Fifty-nine obese children and 35 healthy children aged 6 to 15 years were studied in this prospective comparative study using optical coherence tomography. MCT and PPCT were measured at distances of 500 μm, 1,000 μm, and 1,500 μm from the fovea and optic disc. Three different feature selection algorithms were used to determine the most prominent features of all extracted features. The classification efficiency of the extracted features was analyzed using the RF, SVM, and MLP algorithms, demonstrating their efficacy for distinguishing obese from healthy children. The precision and reliability of measurements were assessed using kappa analysis.

Results: The correlation feature selection algorithm produced the most successful classification results among the different feature selection methods. The most prominent features for distinguishing the obese and healthy groups from each other were PPCT temporal 500 μm, PPCT temporal 1,500 μm, PPCT nasal 1,500 μm, PPCT inferior 1,500 μm, and subfoveal MCT. The classification rates for the RF, SVM, and MLP algorithms were 98.6%, 96.8%, and 89%, respectively.

Conclusion: Obesity has an effect on the choroidal thicknesses of children, particularly in the subfoveal region and the outer semi-circle at 1,500 μm from the optic disc head. Both the RF and SVM algorithms are effective and accurate at classifying obese and healthy children.

References

da Cruz L, Souza J, de Sousa J, Santos A, Cardoso de Paiva A, de Almeida J . Interferometer eye image classification for dry eye categorization using phylogenetic diversity indexes for texture analysis. Comput Methods Programs Biomed. 2019; 188:105269. DOI: 10.1016/j.cmpb.2019.105269. View

Ozcimen M, Sakarya Y, Kurtipek E, Bekci T, Goktas S, Sakarya R . Peripapillary choroidal thickness in patients with chronic obstructive pulmonary disease. Cutan Ocul Toxicol. 2015; 35(1):26-30. DOI: 10.3109/15569527.2015.1004079. View

Ho J, Branchini L, Regatieri C, Krishnan C, Fujimoto J, Duker J . Analysis of normal peripapillary choroidal thickness via spectral domain optical coherence tomography. Ophthalmology. 2011; 118(10):2001-7. PMC: 3184379. DOI: 10.1016/j.ophtha.2011.02.049. View

Cartes C, Lopez D, Salinas D, Segovia C, Ahumada C, Perez N . Dry eye is matched by increased intrasubject variability in tear osmolarity as confirmed by machine learning approach. Arch Soc Esp Oftalmol (Engl Ed). 2019; 94(7):337-342. DOI: 10.1016/j.oftal.2019.03.007. View

Aviles-Rodriguez G, Nieto-Hipolito J, De Los Angeles Cosio-Leon M, Romo-Cardenas G, Sanchez-Lopez J, Radilla-Chavez P . Topological Data Analysis for Eye Fundus Image Quality Assessment. Diagnostics (Basel). 2021; 11(8). PMC: 8394537. DOI: 10.3390/diagnostics11081322. View

Read S, Alonso-Caneiro D, Vincent S, Collins M . Peripapillary choroidal thickness in childhood. Exp Eye Res. 2015; 135:164-73. DOI: 10.1016/j.exer.2015.03.002. View

Lobstein T, Baur L, Uauy R . Obesity in children and young people: a crisis in public health. Obes Rev. 2004; 5 Suppl 1:4-104. DOI: 10.1111/j.1467-789X.2004.00133.x. View

Topcu-Yilmaz P, Akyurek N, Erdogan E . The effect of obesity and insulin resistance on macular choroidal thickness in a pediatric population as assessed by enhanced depth imaging optical coherence tomography. J Pediatr Endocrinol Metab. 2018; 31(8):855-860. DOI: 10.1515/jpem-2018-0079. View

Jayadeva , Khemchandani R, Chandra S . Twin Support Vector Machines for pattern classification. IEEE Trans Pattern Anal Mach Intell. 2007; 29(5):905-10. DOI: 10.1109/tpami.2007.1068. View

10.

Alam A, Mitwalli A, Al-Wakeel J, Chaudhary A, Zebaid M . Plasma fibrinogen and its correlates in adult Saudi population. Saudi Med J. 2004; 25(11):1593-602. View

11.

Svetnik V, Liaw A, Tong C, Culberson J, Sheridan R, Feuston B . Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci. 2003; 43(6):1947-58. DOI: 10.1021/ci034160g. View

12.

Bulus A, Can M, Baytaroglu A, Dereli Can G, Cakmak H, Andiran N . Choroidal Thickness in Childhood Obesity. Ophthalmic Surg Lasers Imaging Retina. 2017; 48(1):10-17. DOI: 10.3928/23258160-20161219-02. View

13.

Cole T, Faith M, Pietrobelli A, Heo M . What is the best measure of adiposity change in growing children: BMI, BMI %, BMI z-score or BMI centile?. Eur J Clin Nutr. 2005; 59(3):419-25. DOI: 10.1038/sj.ejcn.1602090. View

14.

Abramson N, Abramson S . Hypercoagulability: clinical assessment and treatment. South Med J. 2001; 94(10):1013-20. View

15.

Karti O, Nalbantoglu O, Abali S, Tunc S, Ozkan B . The assessment of peripapillary retinal nerve fiber layer and macular ganglion cell layer changes in obese children: a cross-sectional study using optical coherence tomography. Int Ophthalmol. 2016; 37(4):1031-1038. DOI: 10.1007/s10792-016-0371-8. View

16.

Baran R, Baran S, Toraman N, Filiz S, Demirbilek H . Evaluation of intraocular pressure and retinal nerve fiber layer, retinal ganglion cell, central macular thickness, and choroidal thickness using optical coherence tomography in obese children and healthy controls. Niger J Clin Pract. 2019; 22(4):539-545. DOI: 10.4103/njcp.njcp_471_18. View

17.

Lurbe E, Agabiti-Rosei E, Cruickshank J, Dominiczak A, Erdine S, Hirth A . 2016 European Society of Hypertension guidelines for the management of high blood pressure in children and adolescents. J Hypertens. 2016; 34(10):1887-920. DOI: 10.1097/HJH.0000000000001039. View

18.

Komma S, Chhablani J, Ali M, Garudadri C, Senthil S . Comparison of peripapillary and subfoveal choroidal thickness in normal versus primary open-angle glaucoma (POAG) subjects using spectral domain optical coherence tomography (SD-OCT) and swept source optical coherence tomography (SS-OCT). BMJ Open Ophthalmol. 2019; 4(1):e000258. PMC: 6668609. DOI: 10.1136/bmjophth-2018-000258. View

19.

Ruiz Hidalgo I, Rozema J, Saad A, Gatinel D, Rodriguez P, Zakaria N . Validation of an Objective Keratoconus Detection System Implemented in a Scheimpflug Tomographer and Comparison With Other Methods. Cornea. 2017; 36(6):689-695. DOI: 10.1097/ICO.0000000000001194. View

20.

An G, Omodaka K, Tsuda S, Shiga Y, Takada N, Kikawa T . Comparison of Machine-Learning Classification Models for Glaucoma Management. J Healthc Eng. 2018; 2018:6874765. PMC: 6029465. DOI: 10.1155/2018/6874765. View