A huge number of patients in Chennai city are affected by refractive errors. The most common types are myopia, hyperopia, astigmatism and presbyopia among all the types of refractive errors. The variables in the data are refractive errors in both left and right eyes, age, gender, educational status, employment status, nature of job, working hours, working with computer, watching TV, sleeping hours, type of food, extra activity, light in residence, light in work place, family members wearing specs, parents wearing specs, other diseases and other eye disease. In the present work, the results show that fine k-NN and weighted k-NN give better prediction of the refractive errors, when compared to medium, coarse, cosine and cubic k-NN.

KNN method, confusion matrix, ROC curve, refractive error.

Received: November 27, 2021;  Accepted: March 1, 2022; Published: May 12, 2022

How to cite this article: G. Gopi and T. Edwin Prabakaran, k-nearest neighbor method for prediction of refractive errors in patients of Chennai city in India, JP Journal of Biostatistics 20 (2022), 51-63. http://dx.doi.org/10.17654/0973514322013

This Open Access Article is Licensed under Creative Commons Attribution 4.0 International License

References:

[1] Sethu Sheela Devi, Bharani Seelam, Phanindra B. Nukella, Rishi R. Borah, Rahul Ali and Lisa Keay, Prevalence of refractive errors, uncorrected refractive error, and presbyopia in adults in India: a systematic review, Indian Journal of Ophthalmology 67(5) (2019), 583-592.
[2] Xin Li, Gavin S. Chu and Tiago P. Almeida, A KNN classifier for predicting catheter ablation responses using non-contact electrograms during persistent atrial fibrillation, 2018 Computing in Cardiology Conference, 2018, pp. 1-4. DOI:10.22489/CinC.2018.137.
[3] Ram Murat Singh, S. Chatterji and Amod Kumar, Analytical comparison of various types of classifiers for surface EMG signal in order to improve classification accuracy, International Journal of Advanced Research in Engineering and Technology (IJARET) 9(4) (2018), 214-233.
[4] Pradip A. Sarkate and A. V. Deorankar, Classification of chemical medicine or drug using K-nearest neighbor (KNN) and genetic algorithm, International Research Journal of Engineering and Technology (IRJET) 5(3) (2018), 833-834.
[5] Emem Godwin Abraham and Emmanuel Olu Megbelayin, Pattern of refractive errors among ophthalmic outpatients of University of Uyo Teaching Hospital, Uyo, Nigeria, Nigerian Journal of Ophthalmology 23(2) (2015), 39-43.
[6] Hassan Shee Khamis, Kipruto W. Cheruiyot and Stephen Kimani, Application of k-nearest neighbour classification in medical data mining, International Journal of Information and Communication Technology Research 4(4) (2014), 121-128.
[7] B. L. Deekshatulu and Priti Chandra, Classification of heart disease using k-nearest neighbor and genetic algorithm, Procedia Technology 10 (2013), 85-94.
[8] J. S. Raikwal and Kanak Saxena, Performance evaluation of SVM and K-nearest neighbor algorithm over medical data set, International Journal of Computer Applications 50(14) (2012), 35-39.
[9] Mai Shouman, Tim Turner and Rob Stocker, Applying k-nearest neighbour in diagnosing heart disease patients, International Journal of Information and Education Technology 2(3) (2012), 220-223.
[10] Amruta S. Padhye, Rajiv Khandekar, Sheetal Dharmadhikari, Kuldeep Dole, Parikshit Gogate and Madan Deshpande, Prevalence of uncorrected refractive error and other eye problems among urban and rural school children, Middle East African Journal of Ophthalmology 16(2) (2009), 69-74.