{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T01:15:54Z","timestamp":1787274954610,"version":"build-2736575974"},"reference-count":17,"publisher":"Georg Thieme Verlag KG","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Klin Monbl Augenheilkd"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>\n          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.<\/jats:p><jats:p>\n          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).<\/jats:p><jats:p>\n          Results The 17 machine learning algorithms (out of 4 families) varied in root mean squared\/mean absolute prediction error between 0.187\/0.139\u2009mm and 0.255\/0.204\u2009mm (AQD_post) and 0.183\/0.135\u2009mm and 0.253\/0.206\u2009mm (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\u2009mm vs. the best performance Gaussian Process Regression Model with 0.166\/0.159\u2009mm.<\/jats:p><jats:p>\n          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.<\/jats:p>","DOI":"10.1055\/a-1298-8121","type":"journal-article","created":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T13:43:13Z","timestamp":1606225393000},"page":"1430-1437","source":"Crossref","is-referenced-by-count":18,"title":["Artificial Intelligence, Machine Learning and Calculation of Intraocular Lens Power"],"prefix":"10.1055","volume":"237","author":[{"given":"Achim","family":"Langenbucher","sequence":"additional","affiliation":[{"name":"Institut f\u00fcr Experimentelle Ophthalmologie, Universit\u00e4t des Saarlandes, Homburg\/Saar, Deutschland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N\u00f3ra","family":"Szentm\u00e1ry","sequence":"additional","affiliation":[{"name":"Dr. Rolf M. Schwiete-Zentrum f\u00fcr Limbusstammzellforschung und kongenitale Aniridie, Universit\u00e4t des Saarlandes, Saarbr\u00fccken, Deutschland"},{"name":"Klinik f\u00fcr Augenheilkunde, Semmelweis-Universit\u00e4t, Budapest, Ungarn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jascha","family":"Wendelstein","sequence":"additional","affiliation":[{"name":"Abteilung f\u00fcr Augenheilkunde und Optometrie, Johannes-Kepler-Universit\u00e4t Linz, \u00d6sterreich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Hoffmann","sequence":"additional","affiliation":[{"name":"Augen- und Laserklinik Castrop-Rauxel, Deutschland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"194","published-online":{"date-parts":[[2020,11,23]]},"reference":[{"issue":"07","key":"ref1","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1089\/big.2018.0175","article-title":"Effects of distance measure choice on K-nearest neighbour classifier performance: A review","volume":"14","author":"H A Abu Alfeilat","year":"2019","journal-title":"Big Data"},{"key":"ref2","volume-title":"Maschinelles Lernen in der Medizin \u2013 Anwendung von Support Vector Machines in der Ganganalyse [Diplomarbeit]","author":"S Bechtel","year":"2008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-020-0883-3","article-title":"Accuracy of a new intraocular lenspower calculation method based on artificial intelligence","author":"D Carmona Gonz\u00e1lez","year":"2020","journal-title":"Eye (Lond)"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"466","DOI":"10.3928\/1081597X-20200514-02","article-title":"Refractive predictability using the IOLMaster 700 and artificial intelligence-based IOL power formulas compared to standard formulas","volume":"36","author":"H Cheng","year":"2020","journal-title":"J Refract Surg"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.1016\/S0886-3350(97)80034-X","article-title":"Comparison of intraocular lens computations using a neural network versus the Holladay formula","volume":"23","author":"G P Clarke","year":"1997","journal-title":"J Cataract Refract Surg"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-60452-2","volume-title":"Maschinelles Lernen und Wissensbasierte Systeme","author":"J Herrmann","year":"1997"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s00761-019-00679-4","article-title":"K\u00fcnstliche Intelligenz und maschinelles Lernen in der onkologischen Bildgebung","volume":"26","author":"J Kleesiek","year":"2020","journal-title":"Onkologe"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00347-020-01231-1","article-title":"Keratokonusdetektion und Ableitung des Auspr\u00e4gungsgrades aus den Parametern des Corvis ST \u2013 Eine Studie basierend auf Algorithmen des Maschinenlernens","author":"A Langenbucher","year":"2020","journal-title":"Ophthalmologe"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1016\/j.jcrs.2013.10.037","article-title":"C constant: New concept for ray tracing-assisted intraocular lens power calculation","volume":"40","author":"T Olsen","year":"2014","journal-title":"J Cataract Refract Surg"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1016\/j.jcrs.2008.01.015","article-title":"Intraocular lens calculation accuracy limits in normal eyes","volume":"34","author":"P R Preu\u00dfner","year":"2008","journal-title":"J Cataract Refract Surg"},{"key":"ref11","first-page":"1","volume-title":"Big Data im Gesundheitswesen","author":"S R\u00fcping","year":"2019"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"e7202","DOI":"10.7717\/peerj.7202","article-title":"Improving clinical refractive results of cataract surgery by machine learning","volume":"7","author":"M Sramka","year":"2019","journal-title":"PeerJ"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1097\/j.jcrs.0000000000000329","article-title":"Comparison of various intraocular lens formulas using a new high-resolution swept-source optical coherence tomographer","volume":"46","author":"E Szalai","year":"2020","journal-title":"J Cataract Refract Surg"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1365\/s40702-018-0404-z","article-title":"Maschinelles Lernen","volume":"55","author":"A Welsch","year":"2018","journal-title":"HMD"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1097\/APO.0000000000000293","article-title":"Update on intraocular lens formulas and calculations","volume":"9","author":"T Xia","year":"2020","journal-title":"Asia Pac J Ophthalmol (Phila)"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"872","DOI":"10.21037\/atm-20-4706","article-title":"Optical coherence tomography-based deep learning algorithm for quantification of the location of the intraocular lens","volume":"8","author":"C Xin","year":"2020","journal-title":"Ann Transl Med"},{"key":"ref17","volume-title":"Calculating the human Eye, Basics on Biometry","author":"S Scholtz","year":"2020"}],"container-title":["Klinische Monatsbl\u00e4tter f\u00fcr Augenheilkunde"],"original-title":[],"language":"de","link":[{"URL":"http:\/\/www.thieme-connect.de\/products\/ejournals\/pdf\/10.1055\/a-1298-8121.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,7]],"date-time":"2020-12-07T23:42:06Z","timestamp":1607384526000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/a-1298-8121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,23]]},"references-count":17,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2020,12,7]]},"published-print":{"date-parts":[[2020,12]]}},"URL":"https:\/\/doi.org\/10.1055\/a-1298-8121","relation":{},"ISSN":["0023-2165","1439-3999"],"issn-type":[{"value":"0023-2165","type":"print"},{"value":"1439-3999","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,23]]}}}