Evaluation of an artificial intelligence-based intraocular lens calculator: AI-based IOL-optimized formula.

IF 2.6 3区医学 Q2 OPHTHALMOLOGY

Journal of cataract and refractive surgery Pub Date : 2024-12-17 DOI:10.1097/j.jcrs.0000000000001603

Li Wang, Hendrik Burwinkel, Nicolas Bensaid, Douglas D Koch

{"title":"Evaluation of an artificial intelligence-based intraocular lens calculator: AI-based IOL-optimized formula.","authors":"Li Wang, Hendrik Burwinkel, Nicolas Bensaid, Douglas D Koch","doi":"10.1097/j.jcrs.0000000000001603","DOIUrl":null,"url":null,"abstract":"Purpose: To evaluate the ZEISS AI IOL Calculator (ZEISS AI) and compare its accuracy in refractive prediction to the Barrett Universal II (BUII) and Kane formulas.Setting: Cullen Eye Institute, Baylor College of Medicine, Houston, TX.Design: Retrospective case series.Methods: The ZEISS AI IOL Calculator (ZEISS AI) is an artificial intelligence (AI) based IOL-optimized formula. The refractive prediction errors (PEs) were calculated in the entire dataset and subgroups of short eyes (axial length (AL) ≤ 22.5 mm) and long eyes (AL ≥ 25.0 mm). The standard deviation (SD), root-mean-square absolute error (RMSAE), mean absolute error (MAE), median absolute error (MedAE), and percentage of eyes within ±0.25 D, ±0.50 D, ±0.75 D, and ±1.00 D of PEs were calculated. Values with ZEISS AI were compared to those from Barrett Universal II (BUII) and Kane. Advanced statistical methods were applied using R.Results: A dataset of 10,838 eyes was included. Compared to ZEISS AI, BUII produced significantly greater SDs, RMSAEs, and MAEs in the whole group and short eyes, and the Kane had greater SD, RMSAE, and MAE in short eyes (all adjusted P<0.05); the BUII had significantly lower percentages of eyes within ±0.50 D of PEs in the whole group (80.0% vs 81.2%) and in short eyes (71.3% vs. 76.1%), and the Kane had lower percentage of eyes within ±0.50 D of PEs in short eyes (71.9% vs. 76.1%) (all adjusted P<0.05).Conclusion: The ZEISS AI IOL Calculator had superior performance compared to the BUII and Kane formulas, especially in short eyes.","PeriodicalId":15214,"journal":{"name":"Journal of cataract and refractive surgery","volume":" ","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2024-12-17","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.0000000000001603","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: To evaluate the ZEISS AI IOL Calculator (ZEISS AI) and compare its accuracy in refractive prediction to the Barrett Universal II (BUII) and Kane formulas.

Setting: Cullen Eye Institute, Baylor College of Medicine, Houston, TX.

Design: Retrospective case series.

Methods: The ZEISS AI IOL Calculator (ZEISS AI) is an artificial intelligence (AI) based IOL-optimized formula. The refractive prediction errors (PEs) were calculated in the entire dataset and subgroups of short eyes (axial length (AL) ≤ 22.5 mm) and long eyes (AL ≥ 25.0 mm). The standard deviation (SD), root-mean-square absolute error (RMSAE), mean absolute error (MAE), median absolute error (MedAE), and percentage of eyes within ±0.25 D, ±0.50 D, ±0.75 D, and ±1.00 D of PEs were calculated. Values with ZEISS AI were compared to those from Barrett Universal II (BUII) and Kane. Advanced statistical methods were applied using R.

Results: A dataset of 10,838 eyes was included. Compared to ZEISS AI, BUII produced significantly greater SDs, RMSAEs, and MAEs in the whole group and short eyes, and the Kane had greater SD, RMSAE, and MAE in short eyes (all adjusted P<0.05); the BUII had significantly lower percentages of eyes within ±0.50 D of PEs in the whole group (80.0% vs 81.2%) and in short eyes (71.3% vs. 76.1%), and the Kane had lower percentage of eyes within ±0.50 D of PEs in short eyes (71.9% vs. 76.1%) (all adjusted P<0.05).

Conclusion: The ZEISS AI IOL Calculator had superior performance compared to the BUII and Kane formulas, especially in short eyes.

查看原文本刊更多论文

评估基于人工智能的眼内晶状体计算器：基于人工智能的人工晶体优化公式。

目的：评估蔡司人工晶体计算器（ZEISS AI），并将其屈光预测准确性与巴雷特通用II（BUII）和凯恩公式进行比较：德克萨斯州休斯顿贝勒医学院库伦眼科研究所：设计：回顾性病例系列：蔡司人工晶体计算器（ZEISS AI）是一种基于人工智能（AI）的人工晶体优化公式。计算了整个数据集以及短眼（轴向长度 (AL) ≤ 22.5 mm）和长眼（AL ≥ 25.0 mm）亚组的屈光预测误差 (PE)。计算标准偏差 (SD)、均方根绝对误差 (RMSAE)、平均绝对误差 (MAE)、中位数绝对误差 (MedAE) 以及 PE 值在±0.25 D、±0.50 D、±0.75 D 和 ±1.00 D 范围内的眼睛百分比。将 ZEISS AI 的值与 Barrett Universal II (BUII) 和 Kane 的值进行比较。结果：结果：数据集包括 10838 只眼睛。与 ZEISS AI 相比，BUII 在全组和短视眼中产生的 SD、RMSAE 和 MAE 都明显更大，而 Kane 在短视眼中产生的 SD、RMSAE 和 MAE 都更大（所有调整后 PC）：蔡司人工晶体计算器的性能优于 BUII 和 Kane 公式，尤其是在短视眼中。

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

$Journal of cataract and refractive surgery$

Journal of cataract and refractive surgery 医学-外科

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.