Development of machine learning-based models for vault prediction in implantable collamer lens surgery according to implant orientation.

IF 2.6 3区 医学 Q2 OPHTHALMOLOGY
Timoteo González-Cruces, Francisco Javier Aguilar-Salazar, Jordi Marfany Tort, Álvaro Sánchez-Ventosa, Alberto Villarrubia, Jose Lamarca Mateu, Rafael I Barraquer, Sergio Pardina, David Cerdán Palacios, Antonio Cano-Ortiz
{"title":"Development of machine learning-based models for vault prediction in implantable collamer lens surgery according to implant orientation.","authors":"Timoteo González-Cruces, Francisco Javier Aguilar-Salazar, Jordi Marfany Tort, Álvaro Sánchez-Ventosa, Alberto Villarrubia, Jose Lamarca Mateu, Rafael I Barraquer, Sergio Pardina, David Cerdán Palacios, Antonio Cano-Ortiz","doi":"10.1097/j.jcrs.0000000000001623","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>The main objective was to develop a prediction model based on machine learning to calculate the postoperative vault as well as the ideal implantable collamer lens (ICL) size, considering for the first time the implantation orientation in a Caucasian population.</p><p><strong>Setting: </strong>Arruzafa Ophthalmological Hospital (Cordoba, Spain) and Barraquer Ophthalmology Center (Barcelona, Spain).</p><p><strong>Design: </strong>Multicenter, randomized, retrospective study.</p><p><strong>Methods: </strong>Anterior segment biometric data from 235 eyes of patients who underwent ICL lens implantation surgery were collected using the anterior segment optical coherence tomography (AS-OCT) CASIA II, to train and validate five types of multiple regression models based on advanced machine learning techniques. To perform an external validation a dataset of 45 observations was used.</p><p><strong>Results: </strong>The Pearson correlation coefficient between observed and predicted values was similar in the five models in the external validation, with least absolute shrinkage and selection operator (LASSO) regression being the highest (r = 0.62, p < 0.001), followed by random forest regression model (r = 0.60, p < 0.001) and backward stepwise regression (r = 0.58, ρ < 0.001). In addition, the predictions generated by the different models showed closer agreement with the actual vault compared with the Nakamura formulas. Using the new methods, about 70% of the observations had a prediction error below 150 µm.</p><p><strong>Conclusions: </strong>Advanced forms of regressions models based on machine learning allow satisfactory calculation of the ideal lens size, offering greater precision to surgeons customizing surgery according to implant orientation.</p>","PeriodicalId":15214,"journal":{"name":"Journal of cataract and refractive surgery","volume":" ","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of cataract and refractive surgery","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/j.jcrs.0000000000001623","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: The main objective was to develop a prediction model based on machine learning to calculate the postoperative vault as well as the ideal implantable collamer lens (ICL) size, considering for the first time the implantation orientation in a Caucasian population.

Setting: Arruzafa Ophthalmological Hospital (Cordoba, Spain) and Barraquer Ophthalmology Center (Barcelona, Spain).

Design: Multicenter, randomized, retrospective study.

Methods: Anterior segment biometric data from 235 eyes of patients who underwent ICL lens implantation surgery were collected using the anterior segment optical coherence tomography (AS-OCT) CASIA II, to train and validate five types of multiple regression models based on advanced machine learning techniques. To perform an external validation a dataset of 45 observations was used.

Results: The Pearson correlation coefficient between observed and predicted values was similar in the five models in the external validation, with least absolute shrinkage and selection operator (LASSO) regression being the highest (r = 0.62, p < 0.001), followed by random forest regression model (r = 0.60, p < 0.001) and backward stepwise regression (r = 0.58, ρ < 0.001). In addition, the predictions generated by the different models showed closer agreement with the actual vault compared with the Nakamura formulas. Using the new methods, about 70% of the observations had a prediction error below 150 µm.

Conclusions: Advanced forms of regressions models based on machine learning allow satisfactory calculation of the ideal lens size, offering greater precision to surgeons customizing surgery according to implant orientation.

求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
5.60
自引率
14.30%
发文量
259
审稿时长
8.5 weeks
期刊介绍: The Journal of Cataract & Refractive Surgery (JCRS), a preeminent peer-reviewed monthly ophthalmology publication, is the official journal of the American Society of Cataract and Refractive Surgery (ASCRS) and the European Society of Cataract and Refractive Surgeons (ESCRS). JCRS publishes high quality articles on all aspects of anterior segment surgery. In addition to original clinical studies, the journal features a consultation section, practical techniques, important cases, and reviews as well as basic science articles.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信