A Machine Learning Approach for Estimating Visual Acuity Using the Gradient Descent Algorithm

Ibrahim Makama Nickson¹ , Gregory Msksha Wajiga² , Obaka Daniel³

1. Information Technology, Education and Research, Global Integrated Education Volunteers Association, Abuja, Nigeria.
2. Computer Science, School of Pure and Applied Sciences, Modibbo Adama University, Yola, Nigeria.
3. Information Technology, Education and Research, Global Integrated Education Volunteers Association, Abuja, Nigeria.

Section:Research Paper, Product Type: Journal-Paper
Vol.10 , Issue.6 , pp.40-48, Dec-2022

Online published on Dec 31, 2022

Copyright © Ibrahim Makama Nickson, Gregory Msksha Wajiga, Obaka Daniel . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

94 Views    256 Downloads    32 Downloads

Abstract :
About 2.3 billion people worldwide suffer from eye defects, and many do not have access to effective eye diagnosis. The conventional diagnosis of the eye involves measuring the Visual Acuity (VA) using a chart. Researchers have attempted to achieve greater accuracy in VA estimation by developing software systems. However, many software systems have not reasonably improved the diagnosis procedure. This research provides a better approach to estimating VA using machine learning, resulting in a more accurate diagnosis. An Optimized Eye Diagnosis System (OEDS) was developed as a framework for building VA estimating software systems for eye diagnosis. The result is an improved method of estimating VA shown by various plots of the cost function. We have discussed strategies for using a linear regression function to model factors that affect an estimate in medical diagnosis. The theoretical framework developed bridges the gap between the optometrist and a software developer that seeks to build a corrective lens recommendation system based on Artificial Intelligence (AI). We have shown how the accuracy of the VA depends on a number of demographic factors and the detailed procedure for correctly implementing the algorithm on any programming platform illustrated in this work using the Matlab programming language

Key-Words / Index Term :
Machine Learning; Visual Acuity; Gradient Descent; Cost function; Diagnosis

References :
[1] R. Bonetto, V. Latzko, "Computing in Communication Networks in Machine learning,” Academic Press, United States, pp.135-167, 2020.
[2] A. Subasi, "Practical Machine Learning for Data Analysis using Python," Academic Press, United States, pp.34-36, 2020.
[3] R. Russell, “Machine Learning : Step by step guide to implement Machine Learning Algorithms with Python,” CreateSpace Independent Publishing Platform, United States, pp.58-61,2018.
[4] S. Gupta, A. Bhardwaj, A. Mahawar, S. Gupta, "A Case Study of Artificial Intelligence is being used to Reshape Business," International Journal of Electronic, Electronics and Computers, vol. 6, no.3, pp.87-91, 2021.
[5] J. Shabbir and T. Anwer, "Artificial intelligence and its role in near future," Journal of Latex Class Files vol. 14, no.8, pp.1-11, 2018.
[6] R. Michalski, J. Carbonell, T. Mitchell, “Machine Learning: An Artificial Intelligence Approach,” Springer-Verlag, Berlin, pp. 27-30, 1984.
[7] M. Mijwil, D. Salim Mutar, Y. Filali, K. Aggarwal, H. Al-Shahwani, "Comparison between Expert Systems, Machine Learning, and Big Data: An Overview," Asian Journal of Applied Sciences, vol. 10, no. 1, pp. 83 - 88, 2022.
[8] J. Yanase, E. Triantaphyllou, "A Systematic Survey of Computer-Aided Diagnosis in Medicine: Past and Present Developments," Expert Systems with Applications, vol. 138, no.5, pp. 112-821, 2019.
[9] A. Jain, "Machine Learning Techniques for Medical Diagnosis: A Review," In the 2nd International Conference on Science, Technology and Management, India, pp.2449-2459, 2015.
[10] A. Haldorai, R. Arulmurugan, "Supervised, Unsupervised and Reinforcement Learning - A Detailed Perspective," Journal of Advanced Research in Dynamical and Control Systems, vol. 11, no. 6, pp. 429-433, 2019.
[11] E. Benhamou, D. Saltiel, S. Tabachnik, C. Bourdeix, F. Chareyron, B. Guez, "Adaptive Supervised Learning for Volatility Targeting Models,"In the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases , Europe , pp. 1-12, 2021.
[12] C. PatrĂ­cio, J. C. Neves, L. F. Teixeira, "Explainable Deep Learning Methods in Medical Imaging Diagnosis: A Survey," Semantic Scholar, vol. 1, no.1
, pp.420-465, 2022.
[13] C. F. Ubajaka, U. E. Ebenebe1, L. O. Nwankwo, N. B. Egenti, P. O. Adogu, O. S. Ejiofor, "Visual Acuity Status amongst Secondary School Students in South East, Nigeria," American Journal of Medicine and Medical Sciences, vol. 6, no.5, pp. 152-159, 2016.
[14] C. S. Dangare, S. S. Apte, "A Data Mining Approach for Prediction of Heart," International Journal of Computer Engineering & Technology, vol. 3, no.1, pp.30-40, 2012.
[15] M. Janet, S. Sue, E. Anne, "How to measure distance visual acuity," Community Eye Health Journal, vol. 27, no. 85, p. 16, 2014.
[16] E. Cardeso, "Exploring the Ophthalmology with Intellectual and Innovation," Journal of Eye Diseases and Disorders, vol. 5, no.3, pp.127-135, 2020.
[18] K. Jafer, A. Girma, "Prevalence of Refractive Error and Visual Impairment Among Rural School-Age Children of Goro Distric, Gurage Zone, Ethiopia," Ethiopian Journal of Health Sciences, vol. 24, no. 4, pp. 353-358, 2014.
[19] J. D Steinmetz, "Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: the Right to Sight: an analysis for the Global Burden of Disease Study," The Lancet Global Health, vol. 9, no. 2, pp. 144-160, 2021.
[20] K. A. Bhavsar, A. Abugabah, J. Singla, A. A. AlZubi, A. K. Bashir, Nikita, "A Comprehensive Review on Medical Diagnosis Using Machine Learning," Computers,Materials & Continua, vol. 67, no.2, pp.1998-2014, 2021.
[21] T. Mitchell, M. Hill, "Machine Learning," McGraw-Hill Science/Engineering/Math, New York, pp. 414-420, 1997.
[22] P. Ackland, S. Resnikoff, R. Bourne, "World blindness and visual impairment: despite many successess, the problem is growing," Community Eye Health Journal , vol. 30, no.100, pp.71-73, 2017.
[23] C. Hernandez, A. Gil, "Prediction of manifest refraction using machine," Journal of Optometry, vol. 3, no.1, pp. 1-10, 2022.
[24] B. JI, D.S. Yu and S.Y. KimI, "Effect of optical correction by fully corrected glasses on postural stability," Plos One, vol. 7, p. 15-21, 2020.
[25] N. Jemimah, N. D. Oye, "Expert System For Diagnosis Of Eye Defect And Recommendation," International Journal of Computer Trends and Technology, vol. 68, no.2, pp. 34-45, 2020.
[26] I. D.M. Oleske, "Screening and Surveillance for Promoting Population Health,” Epidemiology and the Delivery of Health Care Services, vol.4, no.5, pp.131-150, 2009.
[27] S. J. Leat, C. Yakobchuk-Stanger and E. L. Irving, "Differential visual acuity – A new approach to measuring visual acuity," Journal of Optometry, vol. 13, no. 1, pp. 41-49, 2020.
[28] E. O. Joseph and K. Hannah, "Prevalence and causes of blindness and visual impairment in Limbe urban area, South West Province, Cameroon," Br J Ophthalmol, vol. 91, no.11 pp. 1435–1439, 2007.
[29] V. Praveen, S. S. Suraj, G. Vivek, G. Noopur, K. Atul, "Definition of blindness under National Programme for Control of Blindness: Do we need to revise it?," Indian journal of ophthalmology, vol. 65, no.2, pp.92–96, 2017.
[30] L. Jody, M. Paul, M. Ian, K. Annette, R. Kathryn, "Use of Visual Acuity to Screen for Significant Refractive Errors in Adolescents: Is it Reliable?," Arch Ophthalmol, vol. 128, no.7, pp. 894-899, 2020.
[31] S. N. Muhammad, S. Bilal, A. A. Muhammad, "Intelligent Cardiovascular Disease Prediction Empowered with Gradient Descent Optimization," Heliyon, vol. 7, no.5, pp.7-20, 2021.
[32] J. A. M. Sidey-Gibbons, C. J. Sidey-Gibbons, "Machine learning in medicine: a practical introduction," BMC Medical Research Methodology, vol. 19, no.1, pp.64-72, 2019.
[33] E. Benhamou, D. Saltiel, B. Guez, J. Atif and R. Laraki, "From Forecast to Decisions in Graphical Models: A Natural Gradient Optimization Approach," SSRN Electronic Journal,vol.10, no.2139, pp. 3813401-3813426, 2021.
[34] M. Davison, "Review on Gradient Descent Algorithms in Machine Learning," journal for innovative development in pharmaceutical and technical science, vol. 2, no. 10, pp. 88-93, 2019.
[35] K. Hiroshi, K. Ryosuke, K. Kario and O. Yasushi, "Prediction of blood pressure variability using deep neural networks," International Journal of Medical Informatics, vol. 136, no.104067, pp.1386-5056, 2020.
[36] A. Tyagi, G. Rekha, "Challenges and Application for Implementing Machine Learning in Computer Vision," IGI Global, India, pp. 92-118, 2020.
[37] X. Shi, Z. Chen, H. Wang, D.Y. Yeung, W.K. Wong, W. Woo, "Advances in Neural Information Processing Systems,” NeurIPS, China, pp.1-9, 2005.
[38] C. E. Ojukwu, “Melanoma Skin Cancer Detection Using Support Vector Machines and Convolutional Neural Networks,” International Journal of Scientific Research in Computer Science and Engineering, vol. 9, no.6, pp. 09-12, 2021.

[39] M. M. Pradhan, “ EEG Signal Classification and Human Sensation Recognition Using Machine Learning Techniques,” International Journal of Scientific Research in Computer Science and Engineering, vol. 9, no.1, pp.66-71, 2021.