Network meta-analysis of intraocular lens power calculation formulas based on artificial intelligence in short eyes.

IF 1.7 4区医学 Q3 OPHTHALMOLOGY

BMC Ophthalmology Pub Date : 2025-04-18 DOI:10.1186/s12886-025-04066-z

Xin Zheng, Meng Li, Zhao-Xing Guo, Zhi-Yong Tian, Jing-Shang Zhang, Ying-Yan Mao, Peng Zhao, Zhong-Yan Li, Xiu-Hua Wan

{"title":"Network meta-analysis of intraocular lens power calculation formulas based on artificial intelligence in short eyes.","authors":"Xin Zheng, Meng Li, Zhao-Xing Guo, Zhi-Yong Tian, Jing-Shang Zhang, Ying-Yan Mao, Peng Zhao, Zhong-Yan Li, Xiu-Hua Wan","doi":"10.1186/s12886-025-04066-z","DOIUrl":null,"url":null,"abstract":"Purpose: To systematically assess and compare the accuracy of artificial intelligence (AI) -based intraocular lens (IOL) power calculation formulas with traditional IOL formulas in patients with short eye length.Design: A systematic review and network meta-analysis.Methods: We performed an exhaustive search of the PubMed, Embase, Web of Science, and Cochrane Library databases to identify relevant studies published until February 2024. The extracted data comprised the mean absolute error (MAE) and the percentage of eyes with refractive prediction errors (PE) within ± 0.50 and ± 1.00 diopters (D). Network meta-analysis was performed using Review Manager 5.3 and StataSE 16.0.Results: A network meta-analysis of 21 formulas was carried out in 10 studies, including 756 eyes with axial length (AL) < 22 mm. The results showed that the top AI-based formula was Pearl-DGS. For the percentage of eyes with PE within ± 0.50 D, the Pearl-DGS formula demonstrated the highest accuracy. In terms of the percentage of eyes with PE within ± 1.00 D, the FullMonte IOL formula performed poorly, and no significant differences were observed among the other formulas.Conclusions: The Pearl-DGS formula emerged as the leading AI-based method for determining IOL power in patients with short eye lengths, demonstrating superior accuracy compared to conventional vergence formulas.","PeriodicalId":9058,"journal":{"name":"BMC Ophthalmology","volume":"25 1","pages":"225"},"PeriodicalIF":1.7000,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007189/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Ophthalmology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12886-025-04066-z","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: To systematically assess and compare the accuracy of artificial intelligence (AI) -based intraocular lens (IOL) power calculation formulas with traditional IOL formulas in patients with short eye length.

Design: A systematic review and network meta-analysis.

Methods: We performed an exhaustive search of the PubMed, Embase, Web of Science, and Cochrane Library databases to identify relevant studies published until February 2024. The extracted data comprised the mean absolute error (MAE) and the percentage of eyes with refractive prediction errors (PE) within ± 0.50 and ± 1.00 diopters (D). Network meta-analysis was performed using Review Manager 5.3 and StataSE 16.0.

Results: A network meta-analysis of 21 formulas was carried out in 10 studies, including 756 eyes with axial length (AL) < 22 mm. The results showed that the top AI-based formula was Pearl-DGS. For the percentage of eyes with PE within ± 0.50 D, the Pearl-DGS formula demonstrated the highest accuracy. In terms of the percentage of eyes with PE within ± 1.00 D, the FullMonte IOL formula performed poorly, and no significant differences were observed among the other formulas.

Conclusions: The Pearl-DGS formula emerged as the leading AI-based method for determining IOL power in patients with short eye lengths, demonstrating superior accuracy compared to conventional vergence formulas.

查看原文本刊更多论文

矮眼人工智能人工晶状体度数计算公式的网络meta分析。

目的：系统评估和比较人工智能人工晶状体度数计算公式与传统人工晶状体度数计算公式在短眼长患者中的准确性。设计：系统回顾和网络荟萃分析。方法：我们对PubMed、Embase、Web of Science和Cochrane Library数据库进行了详尽的搜索，以确定截至2024年2月发表的相关研究。提取的数据包括平均绝对误差（MAE）和屈光预测误差（PE）在±0.50和±1.00屈光度范围内的眼睛百分比(D)。使用Review Manager 5.3和StataSE 16.0进行网络荟萃分析。结果：在10项研究中对21个公式进行了网络荟萃分析，其中包括756只眼轴长（AL）。结论：Pearl-DGS公式成为确定短眼长患者IOL度数的主要人工智能方法，与传统的会聚公式相比，它具有更高的准确性。

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

BMC Ophthalmology OPHTHALMOLOGY-

CiteScore

3.40

自引率

5.00%

发文量

441

审稿时长

6-12 weeks

期刊介绍： BMC Ophthalmology is an open access, peer-reviewed journal that considers articles on all aspects of the prevention, diagnosis and management of eye disorders, as well as related molecular genetics, pathophysiology, and epidemiology.