A Novel Management Challenge in Age-Related Macular Degeneration

IF 5.7 Q1 OPHTHALMOLOGY Ophthalmology. Retina Pub Date : 2025-05-01 DOI:10.1016/j.oret.2024.10.029

Gregor S. Reiter MD, PhD , Dmitrii Lachinov MSc , Wolf Bühl MD , Günther Weigert MD , Christoph Grechenig MD , Julia Mai MD , Hrvoje Bogunović PhD , Ursula Schmidt-Erfurth MD

{"title":"A Novel Management Challenge in Age-Related Macular Degeneration","authors":"Gregor S. Reiter MD, PhD , Dmitrii Lachinov MSc , Wolf Bühl MD , Günther Weigert MD , Christoph Grechenig MD , Julia Mai MD , Hrvoje Bogunović PhD , Ursula Schmidt-Erfurth MD","doi":"10.1016/j.oret.2024.10.029","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><div>The progression of geographic atrophy (GA) secondary to age-related macular degeneration is highly variable among individuals. Prediction of the progression is critical to identify patients who will benefit most from the first treatments currently approved. The aim of this study was to investigate the value and difference in predictive power between ophthalmologists and artificial intelligence (AI) in reliably assessing individual speed of GA progression.</div></div><div><h3>Design</h3><div>Prospective, expert and AI comparison study.</div></div><div><h3>Participants</h3><div>Eyes with natural progression of GA from a prospective study (NCT02503332).</div></div><div><h3>Methods</h3><div>Ophthalmologists predicted yearly growth speed of GA as well as selected the potentially faster-growing lesions from 2 eyes based on fundus autofluorescence (FAF), near-infrared reflectance (NIR), and OCT. A deep learning algorithm predicted progression solely on the baseline OCT (Spectralis, Heidelberg Engineering).</div></div><div><h3>Main Outcome Measures</h3><div>Accuracy, weighted κ, and concordance index (c-index) between the prediction made by ophthalmology specialists, ophthalmology residents, and the AI algorithm.</div></div><div><h3>Results</h3><div>A total of 134 eyes of 134 patients from a phase II clinical trial were included; among them, 53 were from the sham arm, and 81 were from untreated fellow eyes. Four ophthalmologists performed 2880 gradings. Human experts reached an accuracy of 0.37, 0.43, and 0.41 and a κ of 0.06, 0.16, and 0.18 on FAF, NIR + OCT, and FAF + NIR + OCT, respectively. On a pairwise comparison task, human experts achieved a c-index of 0.62, 0.59, and 0.60. Automated AI-based analysis reached an accuracy of 0.48 and κ of 0.23 on the first task, and c-index of 0.69 on the second task solely utilizing OCT imaging.</div></div><div><h3>Conclusions</h3><div>Prediction of individual progression will become an important task for patient counseling, most importantly with the treatments becoming available. Human gradings improved with the availability of OCT. However, automated AI performed better than ophthalmologists in several comparisons. Artificial intelligence–supported decisions improve clinical precision, access to timely care for the community, and socioeconomic feasibility in the management of the leading cause of irreversible vision loss.</div></div><div><h3>Financial Disclosure(s)</h3><div>The author(s) have no proprietary or commercial interest in any materials discussed in this article.</div></div>","PeriodicalId":19501,"journal":{"name":"Ophthalmology. Retina","volume":"9 5","pages":"Pages 421-430"},"PeriodicalIF":5.7000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ophthalmology. Retina","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2468653024005323","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose

The progression of geographic atrophy (GA) secondary to age-related macular degeneration is highly variable among individuals. Prediction of the progression is critical to identify patients who will benefit most from the first treatments currently approved. The aim of this study was to investigate the value and difference in predictive power between ophthalmologists and artificial intelligence (AI) in reliably assessing individual speed of GA progression.

Design

Prospective, expert and AI comparison study.

Participants

Eyes with natural progression of GA from a prospective study (NCT02503332).

Methods

Ophthalmologists predicted yearly growth speed of GA as well as selected the potentially faster-growing lesions from 2 eyes based on fundus autofluorescence (FAF), near-infrared reflectance (NIR), and OCT. A deep learning algorithm predicted progression solely on the baseline OCT (Spectralis, Heidelberg Engineering).

Main Outcome Measures

Accuracy, weighted κ, and concordance index (c-index) between the prediction made by ophthalmology specialists, ophthalmology residents, and the AI algorithm.

Results

A total of 134 eyes of 134 patients from a phase II clinical trial were included; among them, 53 were from the sham arm, and 81 were from untreated fellow eyes. Four ophthalmologists performed 2880 gradings. Human experts reached an accuracy of 0.37, 0.43, and 0.41 and a κ of 0.06, 0.16, and 0.18 on FAF, NIR + OCT, and FAF + NIR + OCT, respectively. On a pairwise comparison task, human experts achieved a c-index of 0.62, 0.59, and 0.60. Automated AI-based analysis reached an accuracy of 0.48 and κ of 0.23 on the first task, and c-index of 0.69 on the second task solely utilizing OCT imaging.

Conclusions

Prediction of individual progression will become an important task for patient counseling, most importantly with the treatments becoming available. Human gradings improved with the availability of OCT. However, automated AI performed better than ophthalmologists in several comparisons. Artificial intelligence–supported decisions improve clinical precision, access to timely care for the community, and socioeconomic feasibility in the management of the leading cause of irreversible vision loss.

Financial Disclosure(s)

The author(s) have no proprietary or commercial interest in any materials discussed in this article.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

老年性黄斑变性的新管理挑战：人工智能和专家对地理萎缩的预测。

目的：继发于老年性黄斑变性（AMD）的地理萎缩（GA）在个体间的进展差异很大。要确定哪些患者能从目前批准的首批治疗方法中获益最大，预测病情进展至关重要。本研究旨在调查眼科专家和人工智能（AI）在可靠评估个体GA进展速度方面的价值和预测能力差异：前瞻性、专家与人工智能对比研究：前瞻性研究（NCT02503332）中GA自然进展的眼睛：眼科医生根据眼底自发荧光（FAF）、近红外反射（NIR）和光学相干断层扫描（OCT）预测GA的年生长速度，并从两只眼睛中选择可能生长较快的病变。深度学习算法仅根据基线 OCT（Spectralis，德国海德堡工程公司）预测病情进展：主要结果指标：眼科专家、眼科住院医师和人工智能预测的准确性、加权卡帕（κ）和一致性指数（c-index）：共纳入了一项二期临床试验中 134 名患者的 134 只眼睛，其中 53 只来自假手术组，81 只来自未接受治疗的同组眼睛。四位眼科医生共进行了 2880 次分级。人类专家对 FAF、NIR+OCT 和 FAF+NIR+OCT 的准确度分别为 0.37、0.43 和 0.41，κ 分别为 0.06、0.16 和 0.18。在成对比较任务中，人类专家的 c 指数分别为 0.62、0.59 和 0.60。在第一项任务中，基于人工智能的自动分析准确率为 0.48，κ 为 0.23；在第二项任务中，仅利用 OCT 成像，c 指数为 0.69：结论：个人病情发展预测将成为患者咨询的一项重要任务，最重要的是随着治疗方法的出现。随着 OCT 的出现，人工分级得到了改善。然而，在多项比较中，自动人工智能的表现优于眼科医生。人工智能支持的决策提高了临床精确度，为社区提供了及时的医疗服务，并在管理这一导致不可逆视力丧失的主要原因方面提高了社会经济可行性。

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分钟内获得全文去求助

来源期刊