Machine Learning Model for Predicting Visual Acuity Improvement After Intrastromal Corneal Ring Surgery in Patients With Keratoconus.

IF 2.1 3区医学 Q2 OPHTHALMOLOGY

Cornea Pub Date : 2025-07-23 DOI:10.1097/ICO.0000000000003933

Eva Perez, Nassim Louissi, Sofiene Kallel, Quentin Hays, Nacim Bouheraoua, Malika Hamrani, Anatole Chessel, Vincent Borderie

{"title":"Machine Learning Model for Predicting Visual Acuity Improvement After Intrastromal Corneal Ring Surgery in Patients With Keratoconus.","authors":"Eva Perez, Nassim Louissi, Sofiene Kallel, Quentin Hays, Nacim Bouheraoua, Malika Hamrani, Anatole Chessel, Vincent Borderie","doi":"10.1097/ICO.0000000000003933","DOIUrl":null,"url":null,"abstract":"Background: Keratoconus is a progressive, degenerative corneal disease that can lead to significant visual impairment. The intrastromal ring segment implantation procedure is effective in reshaping the cornea and improving vision. However, vision does not improve postoperatively in all operated eyes, and the results vary widely among patients, making it challenging to predict postoperative visual gain.Purpose: This study investigated the potential of machine learning in predicting postoperative visual acuity in keratoconus patients undergoing intrastromal ring segment implantation with the aim of enhancing surgical decision-making.Methods: This retrospective study analyzed 120 eyes of 102 patients with keratoconus who underwent ring segment implantation (1 symmetric or asymmetric segment, 150-300 μm thick, 150 degrees, or 160 degrees-arc). Preoperative and postoperative refraction, corneal topography, and tomographic data were collected. Various models were trained to predict postoperative visual acuity improvements.Results: The models demonstrated excellent performance, with XGBoost achieving perfect results in predicting whether vision will improve after surgery (R2 = 1.0, Youden Index = 1.0; all test observations being correctly classified). The CatBoost model achieved an R2 of 0.59 [0.7-line mean absolute error (MAE)] for predicting postoperative visual acuity, an R2 of 0.76 (MAE, 1.08 D) for predicting keratometry, and an R2 of 0.54 (MAE, 0.29) for predicting corneal asphericity. Key features for accurate predictions included preoperative keratometry values (K1, K2, Kmax), corneal asphericity, and visual acuity, whereas segment characteristics featured low importance.Conclusions: This study shows the strong potential of machine learning for selecting candidates for surgery and predicting postoperative visual improvements after ring segment implantation in keratoconus eyes.","PeriodicalId":10710,"journal":{"name":"Cornea","volume":" ","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cornea","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/ICO.0000000000003933","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

Background: Keratoconus is a progressive, degenerative corneal disease that can lead to significant visual impairment. The intrastromal ring segment implantation procedure is effective in reshaping the cornea and improving vision. However, vision does not improve postoperatively in all operated eyes, and the results vary widely among patients, making it challenging to predict postoperative visual gain.

Purpose: This study investigated the potential of machine learning in predicting postoperative visual acuity in keratoconus patients undergoing intrastromal ring segment implantation with the aim of enhancing surgical decision-making.

Methods: This retrospective study analyzed 120 eyes of 102 patients with keratoconus who underwent ring segment implantation (1 symmetric or asymmetric segment, 150-300 μm thick, 150 degrees, or 160 degrees-arc). Preoperative and postoperative refraction, corneal topography, and tomographic data were collected. Various models were trained to predict postoperative visual acuity improvements.

Results: The models demonstrated excellent performance, with XGBoost achieving perfect results in predicting whether vision will improve after surgery (R2 = 1.0, Youden Index = 1.0; all test observations being correctly classified). The CatBoost model achieved an R2 of 0.59 [0.7-line mean absolute error (MAE)] for predicting postoperative visual acuity, an R2 of 0.76 (MAE, 1.08 D) for predicting keratometry, and an R2 of 0.54 (MAE, 0.29) for predicting corneal asphericity. Key features for accurate predictions included preoperative keratometry values (K1, K2, Kmax), corneal asphericity, and visual acuity, whereas segment characteristics featured low importance.

Conclusions: This study shows the strong potential of machine learning for selecting candidates for surgery and predicting postoperative visual improvements after ring segment implantation in keratoconus eyes.

查看原文本刊更多论文

预测圆锥角膜患者角膜环内手术后视力改善的机器学习模型。

背景：圆锥角膜是一种进行性退行性角膜疾病，可导致严重的视力损害。角膜内环段植入术能有效地重塑角膜，改善视力。然而，并非所有手术眼的视力都能在术后得到改善，而且患者之间的结果差异很大，这使得预测术后视力恢复具有挑战性。目的：本研究探讨机器学习在圆锥角膜植入术患者术后视力预测中的潜力，以提高手术决策。方法：回顾性分析102例圆锥角膜患者120只眼行环形段植入术（1个对称或非对称节段，150-300 μm厚，150度或160度圆弧）。收集术前和术后屈光、角膜地形图和层析成像数据。训练各种模型来预测术后视力的改善。结果：模型表现优异，其中XGBoost在预测术后视力是否改善方面取得了较好的效果(R2 = 1.0，约登指数= 1.0；所有的测试观察被正确分类)。CatBoost模型预测术后视力的R2为0.59[0.7线平均绝对误差（MAE）]，预测角膜厚度的R2为0.76 (MAE, 1.08 D)，预测角膜非球形的R2为0.54 （MAE, 0.29）。准确预测的关键特征包括术前角膜测量值（K1、K2、Kmax）、角膜非球面度和视力，而节段特征的重要性较低。结论：本研究显示了机器学习在圆锥角膜环段植入术后选择手术候选人和预测术后视力改善方面的强大潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Cornea 医学-眼科学

CiteScore

5.20

自引率

10.70%

发文量

354

审稿时长

3-6 weeks

期刊介绍： For corneal specialists and for all general ophthalmologists with an interest in this exciting subspecialty, Cornea brings together the latest clinical and basic research on the cornea and the anterior segment of the eye. Each volume is peer-reviewed by Cornea''s board of world-renowned experts and fully indexed in archival format. Your subscription brings you the latest developments in your field and a growing library of valuable professional references. Sponsored by The Cornea Society which was founded as the Castroviejo Cornea Society in 1975.