Artificial intelligence-based model for the interpretation and reporting of standard automated perimetry.

IF 1.2 4区 医学 Q3 OPHTHALMOLOGY
Arquivos brasileiros de oftalmologia Pub Date : 2025-07-21 eCollection Date: 2025-01-01 DOI:10.5935/0004-2749.2024-0270
Joacy Pedro Franco David, Alexandre Antonio Marques Rosa, Rafael Scherer, Cláudio Eduardo Corrêa Teixeira, Douglas Costa
{"title":"Artificial intelligence-based model for the interpretation and reporting of standard automated perimetry.","authors":"Joacy Pedro Franco David, Alexandre Antonio Marques Rosa, Rafael Scherer, Cláudio Eduardo Corrêa Teixeira, Douglas Costa","doi":"10.5935/0004-2749.2024-0270","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Standard automated perimetry has been the standard method for measuring visual field changes for several years. It can measure an individual's ability to detect a light stimulus from a uniformly illuminated background. In the management of glaucoma, the primary objective of perimetry is the identification and quantification of visual field abnormalities. It also serves as a longitudinal evaluation for the detection of disease progression. The development of artificial intelligence--based models capable of interpreting tests could combine technological development with improved access to healthcare.</p><p><strong>Methods: </strong>In this observational, cross-sectional, descriptive study, we used an artificial intelligence-based model [Inception V3] to interpret gray-scale crops from standard automated perimetry that were performed in an ophthalmology clinic in the Brazilian Amazon rainforest between January 2018 and December 2022.</p><p><strong>Results: </strong>The study included 1,519 standard automated perimetry test results that were performed using Humphrey HFA-II-i-750 (Zeiss Meditech). The Subsequently, 70%, 10%, and 20% of the dataset were used for training, validation, and testing, respectively. The model achieved 80% (68.23%-88.9%) sensitivity and 94.64% (88.8%-98%) specificity for detecting altered perimetry results. Furthermore, the area under the receiver operating characteristic curve was 0.93.</p><p><strong>Conclusions: </strong>The integration of artificial intelligence in the diagnosis, screening, and monitoring of pathologies represents a paradigm shift in ophthalmology, enabling significant improvements in safety, efficiency, availability, and accessibility of treatment.</p>","PeriodicalId":8397,"journal":{"name":"Arquivos brasileiros de oftalmologia","volume":"88 5","pages":"e20240270"},"PeriodicalIF":1.2000,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Arquivos brasileiros de oftalmologia","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.5935/0004-2749.2024-0270","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: Standard automated perimetry has been the standard method for measuring visual field changes for several years. It can measure an individual's ability to detect a light stimulus from a uniformly illuminated background. In the management of glaucoma, the primary objective of perimetry is the identification and quantification of visual field abnormalities. It also serves as a longitudinal evaluation for the detection of disease progression. The development of artificial intelligence--based models capable of interpreting tests could combine technological development with improved access to healthcare.

Methods: In this observational, cross-sectional, descriptive study, we used an artificial intelligence-based model [Inception V3] to interpret gray-scale crops from standard automated perimetry that were performed in an ophthalmology clinic in the Brazilian Amazon rainforest between January 2018 and December 2022.

Results: The study included 1,519 standard automated perimetry test results that were performed using Humphrey HFA-II-i-750 (Zeiss Meditech). The Subsequently, 70%, 10%, and 20% of the dataset were used for training, validation, and testing, respectively. The model achieved 80% (68.23%-88.9%) sensitivity and 94.64% (88.8%-98%) specificity for detecting altered perimetry results. Furthermore, the area under the receiver operating characteristic curve was 0.93.

Conclusions: The integration of artificial intelligence in the diagnosis, screening, and monitoring of pathologies represents a paradigm shift in ophthalmology, enabling significant improvements in safety, efficiency, availability, and accessibility of treatment.

基于人工智能的标准自动视界判读和报告模型。
目的:多年来,标准自动视距法一直是测量视野变化的标准方法。它可以测量一个人从均匀照明的背景中检测光刺激的能力。在青光眼的治疗中,视野检查的主要目的是识别和量化视野异常。它还可以作为疾病进展检测的纵向评估。开发能够解释测试结果的基于人工智能的模型,可以将技术发展与改善医疗保健服务结合起来。方法:在这项观察性、横断面、描述性研究中,我们使用基于人工智能的模型[Inception V3]来解释2018年1月至2022年12月期间在巴西亚马逊雨林眼科诊所进行的标准自动视距测量的灰度作物。结果:该研究包括1,519个标准的自动视界检查结果,使用Humphrey HFA-II-i-750(蔡司Meditech)进行。随后,数据集的70%、10%和20%分别用于训练、验证和测试。该模型检测视野变化的灵敏度为80%(68.23% ~ 88.9%),特异性为94.64%(88.8% ~ 98%)。受试者工作特征曲线下面积为0.93。结论:人工智能在病理诊断、筛查和监测中的集成代表了眼科的范式转变,使治疗的安全性、效率、可获得性和可及性得到显著提高。
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
CiteScore
1.60
自引率
0.00%
发文量
200
审稿时长
6-12 weeks
期刊介绍: The ABO-ARQUIVOS BRASILEIROS DE OFTALMOLOGIA (ABO, ISSN 0004-2749 - print and ISSN 1678-2925 - (ABO, ISSN 0004-2749 - print and ISSN 1678-2925 - electronic version), the official bimonthly publication of the Brazilian Council of Ophthalmology (CBO), aims to disseminate scientific studies in Ophthalmology, Visual Science and Health public, by promoting research, improvement and updating of professionals related to the field.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信