Artificial Intelligence, Machine Learning and Calculation of Intraocular Lens Power

Abstract

Background and Purpose In the last decade, artificial intelligence and machine learning algorithms have been more and more established for the screening and detection of diseases and pathologies, as well as for describing interactions between measures where classical methods are too complex or fail. The purpose of this paper is to model the measured postoperative position of an intraocular lens implant after cataract surgery, based on preoperatively assessed biometric effect sizes using techniques of machine learning.

Patients and Methods In this study, we enrolled 249 eyes of patients who underwent elective cataract surgery at Augenklinik Castrop-Rauxel. Eyes were measured preoperatively with the IOLMaster 700 (Carl Zeiss Meditec), as well as preoperatively and postoperatively with the Casia 2 OCT (Tomey). Based on preoperative effect sizes axial length, corneal thickness, internal anterior chamber depth, thickness of the crystalline lens, mean corneal radius and corneal diameter a selection of 17 machine learning algorithms were tested for prediction performance for calculation of internal anterior chamber depth (AQD_post) and axial position of equatorial plane of the lens in the pseudophakic eye (LEQ_post).

Results The 17 machine learning algorithms (out of 4 families) varied in root mean squared/mean absolute prediction error between 0.187/0.139 mm and 0.255/0.204 mm (AQD_post) and 0.183/0.135 mm and 0.253/0.206 mm (LEQ_post), using 5-fold cross validation techniques. The Gaussian Process Regression Model using an exponential kernel showed the best performance in terms of root mean squared error for prediction of AQDpost and LEQpost. If the entire dataset is used (without splitting for training and validation data), comparison of a simple multivariate linear regression model vs. the algorithm with the best performance showed a root mean squared prediction error for AQD_post/LEQ_post with 0.188/0.187 mm vs. the best performance Gaussian Process Regression Model with 0.166/0.159 mm.

Conclusion In this paper we wanted to show the principles of supervised machine learning applied to prediction of the measured physical postoperative axial position of the intraocular lenses. Based on our limited data pool and the algorithms used in our setting, the benefit of machine learning algorithms seems to be limited compared to a standard multivariate regression model.

Key words

artificial intelligence - machine learning - IOL power calculation - cataract surgery

Publication History

Received: 11 September 2020

Accepted: 26 October 2020

Article published online:
23 November 2020

• References/Literatur

• 1 Abu Alfeilat HA, Hassanat ABA, Lasassmeh O. et al. Effects of distance measure choice on K-nearest neighbour classifier performance: A review. Big Data 2019; 14 (07) 221-248
• 2 Bechtel S. Maschinelles Lernen in der Medizin – Anwendung von Support Vector Machines in der Ganganalyse [Diplomarbeit]. Saarbrücken: Fachbereich Mathematik, Universität des Saarlandes; 2008
• 3 Carmona González D, Palomino Bautista C. Accuracy of a new intraocular lenspower calculation method based on artificial intelligence. Eye (Lond) 2020;
• 4 Cheng H, Kane JX, Liu L. et al. Refractive predictability using the IOLMaster 700 and artificial intelligence-based IOL power formulas compared to standard formulas. J Refract Surg 2020; 36: 466-472
• 5 Clarke GP, Burmeister J. Comparison of intraocular lens computations using a neural network versus the Holladay formula. J Cataract Refract Surg 1997; 23: 1585-1589
• 6 Herrmann J. Maschinelles Lernen und Wissensbasierte Systeme. Heidelberg: Springer; 1997
• 7 Kleesiek J, Murray JM, Kaissis G, Braren R. Künstliche Intelligenz und maschinelles Lernen in der onkologischen Bildgebung. Onkologe 2020; 26: 60-65
• 8 Langenbucher A, Häfner L, Eppig T. et al. Keratokonusdetektion und Ableitung des Ausprägungsgrades aus den Parametern des Corvis ST – Eine Studie basierend auf Algorithmen des Maschinenlernens. Ophthalmologe 2020;
• 9 Olsen T, Hoffmann PC. C constant: New concept for ray tracing-assisted intraocular lens power calculation. J Cataract Refract Surg 2014; 40: 764-773
• 10 Preußner PR, Olsen T, Hoffmann PC. et al. Intraocular lens calculation accuracy limits in normal eyes. J Cataract Refract Surg 2008; 34: 802-808
• 11 Rüping S, Sander J. Big Data im Gesundheitswesen. In: Haring R. Hrsg. Gesundheit digital: Perspektiven zur Digitalisierung im Gesundheitswesen. Heidelberg: Springer; 2019: 1-31
• 12 Sramka M, Slovak M, Tuckova J. et al. Improving clinical refractive results of cataract surgery by machine learning. PeerJ 2019; 7: e7202 doi:10.7717/peerj.7202
• 13 Szalai E, Toth N, Kolkedi Z. et al. Comparison of various intraocular lens formulas using a new high-resolution swept-source optical coherence tomographer. J Cataract Refract Surg 2020; 46: 1138-1141 doi:10.1097/j.jcrs.0000000000000329
• 14 Welsch A, Eitle V, Buxmann P. Maschinelles Lernen. HMD 2018; 55: 366-382 doi:10.1365/s40702-018-0404-z
• 15 Xia T, Martinez CE, Tsai LM. Update on intraocular lens formulas and calculations. Asia Pac J Ophthalmol (Phila) 2020; 9: 186-193 doi:10.1097/APO.0000000000000293
• 16 Xin C, Bian GB, Zhang H, Liu W, Dong Z. Optical coherence tomography-based deep learning algorithm for quantification of the location of the intraocular lens. Ann Transl Med 2020; 8: 872
• 17 Scholtz S, Cayless A, Langenbucher A. Calculating the human Eye, Basics on Biometry. In: Liu C, Shalaby Bardan A. eds. Cataract Surgery. Berlin: Springer; 2020