Advanced Artificial-Intelligence-Based Jiang Formula for Intraocular Lens Power in Congenital Ectopia Lentis.

IF 2.6 3区医学 Q2 OPHTHALMOLOGY Translational Vision Science & Technology Pub Date : 2025-02-03 DOI:10.1167/tvst.14.2.5

Yan Liu, Xinyue Wang, Linghao Song, Yang Sun, Zexu Chen, Wannan Jia, Xin Shen, Yalei Wang, Xinyao Chen, Qiuyi Huo, Pranav Prakash Edavi, Tianhui Chen, Yongxiang Jiang

{"title":"Advanced Artificial-Intelligence-Based Jiang Formula for Intraocular Lens Power in Congenital Ectopia Lentis.","authors":"Yan Liu, Xinyue Wang, Linghao Song, Yang Sun, Zexu Chen, Wannan Jia, Xin Shen, Yalei Wang, Xinyao Chen, Qiuyi Huo, Pranav Prakash Edavi, Tianhui Chen, Yongxiang Jiang","doi":"10.1167/tvst.14.2.5","DOIUrl":null,"url":null,"abstract":"Purpose: The purpose of this study was to develop an artificial intelligence (AI)-based intraocular lens (IOLs) power calculation formula for improving the accuracy of IOLs power calculations in patients with congenital ectopia lentis (CEL).Methods: A total of 651 eyes with CEL that underwent IOLs implantation surgery were included in this study. An AI-based ensemble formula-the Jiang Formula, was developed using a training dataset of 520 eyes and evaluated on a testing dataset of 131 eyes. A five-fold cross-validation and a two-layer ensemble learning model were constructed. The formula was then tested in a test set and compared against five current classic formulas.Results: The cohort included young patients (mean age = 14.38 ± 13.35 years). The Jiang Formula showed the lowest prediction error (PE; = 0.08 ± 1.01 diopters [D]), absolute error (AE; = 0.77 ± 0.65 D), median absolute error (MedAE; = 0.66 D), and root mean square error (RMSE; = 1.02 D) among six formulas (P < 0.001). Moreover, 68.00% of the eyes in the test set had AE within 1.0 D in the Jiang Formula.Conclusions: AI-integrated two-layer ensemble learning model demonstrates promising applications in IOLs power calculations for patients with CEL, not only providing higher predictive accuracy than current classic formulas but also accommodating extreme values and variations in surgical techniques.Translational relevance: The Jiang Formula, an AI-integrated two-layer ensemble learning model, enhances IOLs power calculation accuracy in patients with CEL, ultimately improving surgical outcomes and supporting more effective, personalized treatment in this unique patient group.","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"14 2","pages":"5"},"PeriodicalIF":2.6000,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11801393/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Translational Vision Science & Technology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1167/tvst.14.2.5","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 purpose of this study was to develop an artificial intelligence (AI)-based intraocular lens (IOLs) power calculation formula for improving the accuracy of IOLs power calculations in patients with congenital ectopia lentis (CEL).

Methods: A total of 651 eyes with CEL that underwent IOLs implantation surgery were included in this study. An AI-based ensemble formula-the Jiang Formula, was developed using a training dataset of 520 eyes and evaluated on a testing dataset of 131 eyes. A five-fold cross-validation and a two-layer ensemble learning model were constructed. The formula was then tested in a test set and compared against five current classic formulas.

Results: The cohort included young patients (mean age = 14.38 ± 13.35 years). The Jiang Formula showed the lowest prediction error (PE; = 0.08 ± 1.01 diopters [D]), absolute error (AE; = 0.77 ± 0.65 D), median absolute error (MedAE; = 0.66 D), and root mean square error (RMSE; = 1.02 D) among six formulas (P < 0.001). Moreover, 68.00% of the eyes in the test set had AE within 1.0 D in the Jiang Formula.

Conclusions: AI-integrated two-layer ensemble learning model demonstrates promising applications in IOLs power calculations for patients with CEL, not only providing higher predictive accuracy than current classic formulas but also accommodating extreme values and variations in surgical techniques.

Translational relevance: The Jiang Formula, an AI-integrated two-layer ensemble learning model, enhances IOLs power calculation accuracy in patients with CEL, ultimately improving surgical outcomes and supporting more effective, personalized treatment in this unique patient group.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于人工智能的先进人工晶状体屈光度姜配方治疗先天性晶状体异位。

目的：研究基于人工智能（AI）的人工晶状体（iol）度数计算公式，以提高先天性晶状体异位（CEL）患者人工晶状体度数计算的准确性。方法：对651例行人工晶状体植入术的CEL眼进行研究。使用520只眼睛的训练数据集开发了一个基于人工智能的集成公式——Jiang公式，并在131只眼睛的测试数据集上进行了评估。构建了五重交叉验证和两层集成学习模型。然后在一个测试集中对该公式进行了测试，并与当前的五个经典公式进行了比较。结果：该队列包括年轻患者（平均年龄= 14.38±13.35岁）。Jiang公式预测误差最小(PE；= 0.08±1.01屈光度[D])，绝对误差(AE；= 0.77±0.65 D)，中位绝对误差(MedAE；= 0.66 D)，均方根误差(RMSE；= 1.02 D)，差异有统计学意义（P < 0.001）。在蒋式中，68.00%的试验组的AE在1.0 D以内。结论：人工智能集成的两层集成学习模型在CEL患者的人工晶状体度数计算中具有良好的应用前景，不仅比目前的经典公式提供更高的预测精度，而且可以适应手术技术的极端值和变化。翻译相关性：Jiang公式是一种人工智能集成的双层集成学习模型，可提高CEL患者人工晶状体度数计算的准确性，最终改善手术结果，并支持对这一独特患者群体进行更有效、个性化的治疗。

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分钟内获得全文去求助

来源期刊

Translational Vision Science & Technology Engineering-Biomedical Engineering

CiteScore

5.70

自引率

3.30%

发文量

346

审稿时长

25 weeks

期刊介绍： Translational Vision Science & Technology (TVST), an official journal of the Association for Research in Vision and Ophthalmology (ARVO), an international organization whose purpose is to advance research worldwide into understanding the visual system and preventing, treating and curing its disorders, is an online, open access, peer-reviewed journal emphasizing multidisciplinary research that bridges the gap between basic research and clinical care. A highly qualified and diverse group of Associate Editors and Editorial Board Members is led by Editor-in-Chief Marco Zarbin, MD, PhD, FARVO. The journal covers a broad spectrum of work, including but not limited to: Applications of stem cell technology for regenerative medicine, Development of new animal models of human diseases, Tissue bioengineering, Chemical engineering to improve virus-based gene delivery, Nanotechnology for drug delivery, Design and synthesis of artificial extracellular matrices, Development of a true microsurgical operating environment, Refining data analysis algorithms to improve in vivo imaging technology, Results of Phase 1 clinical trials, Reverse translational ("bedside to bench") research. TVST seeks manuscripts from scientists and clinicians with diverse backgrounds ranging from basic chemistry to ophthalmic surgery that will advance or change the way we understand and/or treat vision-threatening diseases. TVST encourages the use of color, multimedia, hyperlinks, program code and other digital enhancements.