筛选心房颤动患者的认知障碍：基于视网膜眼底照片的深度学习模型

IF 2.5 Q2 CARDIAC & CARDIOVASCULAR SYSTEMS

Heart Rhythm O2 Pub Date : 2025-05-01 DOI:10.1016/j.hroo.2025.01.019

Zhen Wang MD , Mingxiao Li MD , Peng Xia BS , Chao Jiang MD , Ting Shen MD , Jiaming Ma MD , Yu Bai MD , Suhui Zhang MD , Yiwei Lai MD , Sitong Li MS , Hui Xu MD , Yang Xu MD , Tong Ma MS , Lie Ju PhD , Liu He PhD , Li Dong MD , Caihua Sang MD , Deyong Long MD , Yuzhong Chen PhD , Xin Du MD , Changsheng Ma MD

{"title":"筛选心房颤动患者的认知障碍：基于视网膜眼底照片的深度学习模型","authors":"Zhen Wang MD , Mingxiao Li MD , Peng Xia BS , Chao Jiang MD , Ting Shen MD , Jiaming Ma MD , Yu Bai MD , Suhui Zhang MD , Yiwei Lai MD , Sitong Li MS , Hui Xu MD , Yang Xu MD , Tong Ma MS , Lie Ju PhD , Liu He PhD , Li Dong MD , Caihua Sang MD , Deyong Long MD , Yuzhong Chen PhD , Xin Du MD , Changsheng Ma MD","doi":"10.1016/j.hroo.2025.01.019","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Patients with atrial fibrillation (AF) have a higher risk of cognitive impairment (CI). However, complexity of CI diagnosis and lack of simple screening approaches limited early screening and intervention of CI in AF patients.</div></div><div><h3>Objective</h3><div>Our study aimed to develop deep learning models based on fundus photographs for easy screening of CI in AF patients.</div></div><div><h3>Methods</h3><div>From May 2021 to April 2023, patients who completed fundus examination and cognitive function evaluation in the Chinese Atrial Fibrillation Registry Study were included. The training and validation sets were randomly split at an 8:2 ratio. Participants from the Beijing Eye Study served as the external validation set. Different deep learning models were trained, and their CI detection ability was validated.</div></div><div><h3>Results</h3><div>A total of 899 patients in the Chinese Atrial Fibrillation Registry Study were included. In the validation set, the vision-ensemble model based on fundus images alone had an area under the receiver-operating characteristic curve (AUROC) of 0.855 (95% confidence interval 0.816–0.894) for CI screening. The multimodal model (AUROC 0.861, 95% confidence interval 0.823–0.898), based on fundus photographs and 4 clinical variables, performed comparably to the vision-ensemble model. The AUROC of the vision-ensemble model for CI screening achieved 0.773 (95% confidence interval 0.709–0.837) in the external test set. In the saliency map, the vision-ensemble model focused on areas around retinal vessels and the optic disc.</div></div><div><h3>Conclusion</h3><div>A vision-ensemble model based on fundus images might be practical for preliminary screening of CI in AF patients.</div></div>","PeriodicalId":29772,"journal":{"name":"Heart Rhythm O2","volume":"6 5","pages":"Pages 678-686"},"PeriodicalIF":2.5000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Screening cognitive impairment in patients with atrial fibrillation: A deep learning model based on retinal fundus photographs\",\"authors\":\"Zhen Wang MD , Mingxiao Li MD , Peng Xia BS , Chao Jiang MD , Ting Shen MD , Jiaming Ma MD , Yu Bai MD , Suhui Zhang MD , Yiwei Lai MD , Sitong Li MS , Hui Xu MD , Yang Xu MD , Tong Ma MS , Lie Ju PhD , Liu He PhD , Li Dong MD , Caihua Sang MD , Deyong Long MD , Yuzhong Chen PhD , Xin Du MD , Changsheng Ma MD\",\"doi\":\"10.1016/j.hroo.2025.01.019\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>Patients with atrial fibrillation (AF) have a higher risk of cognitive impairment (CI). However, complexity of CI diagnosis and lack of simple screening approaches limited early screening and intervention of CI in AF patients.</div></div><div><h3>Objective</h3><div>Our study aimed to develop deep learning models based on fundus photographs for easy screening of CI in AF patients.</div></div><div><h3>Methods</h3><div>From May 2021 to April 2023, patients who completed fundus examination and cognitive function evaluation in the Chinese Atrial Fibrillation Registry Study were included. The training and validation sets were randomly split at an 8:2 ratio. Participants from the Beijing Eye Study served as the external validation set. Different deep learning models were trained, and their CI detection ability was validated.</div></div><div><h3>Results</h3><div>A total of 899 patients in the Chinese Atrial Fibrillation Registry Study were included. In the validation set, the vision-ensemble model based on fundus images alone had an area under the receiver-operating characteristic curve (AUROC) of 0.855 (95% confidence interval 0.816–0.894) for CI screening. The multimodal model (AUROC 0.861, 95% confidence interval 0.823–0.898), based on fundus photographs and 4 clinical variables, performed comparably to the vision-ensemble model. The AUROC of the vision-ensemble model for CI screening achieved 0.773 (95% confidence interval 0.709–0.837) in the external test set. In the saliency map, the vision-ensemble model focused on areas around retinal vessels and the optic disc.</div></div><div><h3>Conclusion</h3><div>A vision-ensemble model based on fundus images might be practical for preliminary screening of CI in AF patients.</div></div>\",\"PeriodicalId\":29772,\"journal\":{\"name\":\"Heart Rhythm O2\",\"volume\":\"6 5\",\"pages\":\"Pages 678-686\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2025-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Heart Rhythm O2\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2666501825000455\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Heart Rhythm O2","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666501825000455","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

摘要

背景：房颤（AF）患者发生认知障碍（CI）的风险较高。然而，CI诊断的复杂性和缺乏简单的筛查方法限制了AF患者CI的早期筛查和干预。目的：建立基于眼底照片的深度学习模型，用于房颤患者CI筛查。方法纳入2021年5月至2023年4月在中国房颤登记研究中完成眼底检查和认知功能评估的患者。训练集和验证集按8:2的比例随机分割。来自北京眼科研究的参与者作为外部验证集。对不同深度学习模型进行训练，验证其CI检测能力。结果中国房颤登记研究共纳入899例患者。在验证集中，仅基于眼底图像的视觉集成模型用于CI筛选的接受者工作特征曲线（AUROC）下面积为0.855（95%置信区间为0.816-0.894）。基于眼底照片和4个临床变量的多模态模型（AUROC为0.861,95%可信区间为0.823-0.898）的效果与视觉集成模型相当。视觉集成模型用于CI筛选的AUROC在外部测试集中达到0.773（95%置信区间0.709-0.837）。在显著性图中，视觉集成模型聚焦于视网膜血管和视盘周围的区域。结论基于眼底图像的视觉集成模型可用于房颤患者CI的初步筛查。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Screening cognitive impairment in patients with atrial fibrillation: A deep learning model based on retinal fundus photographs

Background

Patients with atrial fibrillation (AF) have a higher risk of cognitive impairment (CI). However, complexity of CI diagnosis and lack of simple screening approaches limited early screening and intervention of CI in AF patients.

Objective

Our study aimed to develop deep learning models based on fundus photographs for easy screening of CI in AF patients.

Methods

From May 2021 to April 2023, patients who completed fundus examination and cognitive function evaluation in the Chinese Atrial Fibrillation Registry Study were included. The training and validation sets were randomly split at an 8:2 ratio. Participants from the Beijing Eye Study served as the external validation set. Different deep learning models were trained, and their CI detection ability was validated.

Results

A total of 899 patients in the Chinese Atrial Fibrillation Registry Study were included. In the validation set, the vision-ensemble model based on fundus images alone had an area under the receiver-operating characteristic curve (AUROC) of 0.855 (95% confidence interval 0.816–0.894) for CI screening. The multimodal model (AUROC 0.861, 95% confidence interval 0.823–0.898), based on fundus photographs and 4 clinical variables, performed comparably to the vision-ensemble model. The AUROC of the vision-ensemble model for CI screening achieved 0.773 (95% confidence interval 0.709–0.837) in the external test set. In the saliency map, the vision-ensemble model focused on areas around retinal vessels and the optic disc.