Yi Ye, Wei Feng, Yaodong Ding, Qing Chen, Yang Zhang, Li Lin, Peng Xia, Tong Ma, Lie Ju, Bin Wang, Xiangang Chang, Xiaoyi Wang, Longjun Cai, Zongyuan Ge, Yong Zeng
{"title":"Retinal image-based deep learning for mild cognitive impairment detection in coronary artery disease population.","authors":"Yi Ye, Wei Feng, Yaodong Ding, Qing Chen, Yang Zhang, Li Lin, Peng Xia, Tong Ma, Lie Ju, Bin Wang, Xiangang Chang, Xiaoyi Wang, Longjun Cai, Zongyuan Ge, Yong Zeng","doi":"10.1136/heartjnl-2024-325486","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Coronary artery disease (CAD) is linked to an increased risk of mild cognitive impairment (MCI). Effective and convenient screening methods for identifying MCI from the CAD population are still lacking. This study aims to develop a deep learning model using fundus images to optimise MCI diagnosis in the CAD population, achieving early intervention and improving prognosis.</p><p><strong>Methods: </strong>Patients with CAD (at least one ≥50% stenosis) from July 2021 to July 2023 at Beijing Anzhen Hospital were included in the single-centre cross-sectional study. Eligible patients from July 2021 to May 2023 were randomly assigned in an 8:2 ratio for training and internal testing of the model. Patients enrolled from June 2023 to July 2023 were included in the external validation group. Four different convolutional neural network architectures were used to train the subjects' fundus images. The reference standards were a Mini-Mental State Examination (MMSE) score of <27 and a Montreal Cognitive Assessment (MoCA) score of <26, respectively. A comprehensive visual model of MCI detection was established through model integration.</p><p><strong>Results: </strong>A total of 9009 eligible images from 4357 patients with CAD were collected. The artificial intelligence (AI) algorithm based on the MMSE achieved an area under the curve (AUC) of 0.832 (95% CI 0.800 to 0.863) in the test group and 0.776 (95% CI 0.730 to 0.821) in the validation group. The AI algorithm based on the MoCA achieved an AUC of 0.764 (95% CI 0.742 to 0.785) in the test group and 0.725 (95% CI 0.701 to 0.750) in the validation group. The calibration curves of the internal test sets of the two models exhibited a good calibration effect. The results of decision curves revealed extensive clinical application value.</p><p><strong>Conclusion: </strong>The AI algorithm trained on fundus images in this study exerted promising performance in screening MCI in the CAD population and might be a non-invasive and effective alternative for early diagnosis of the disease.</p><p><strong>Trial registration number: </strong>NCT06102226.</p>","PeriodicalId":12835,"journal":{"name":"Heart","volume":" ","pages":""},"PeriodicalIF":5.1000,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Heart","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1136/heartjnl-2024-325486","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Coronary artery disease (CAD) is linked to an increased risk of mild cognitive impairment (MCI). Effective and convenient screening methods for identifying MCI from the CAD population are still lacking. This study aims to develop a deep learning model using fundus images to optimise MCI diagnosis in the CAD population, achieving early intervention and improving prognosis.
Methods: Patients with CAD (at least one ≥50% stenosis) from July 2021 to July 2023 at Beijing Anzhen Hospital were included in the single-centre cross-sectional study. Eligible patients from July 2021 to May 2023 were randomly assigned in an 8:2 ratio for training and internal testing of the model. Patients enrolled from June 2023 to July 2023 were included in the external validation group. Four different convolutional neural network architectures were used to train the subjects' fundus images. The reference standards were a Mini-Mental State Examination (MMSE) score of <27 and a Montreal Cognitive Assessment (MoCA) score of <26, respectively. A comprehensive visual model of MCI detection was established through model integration.
Results: A total of 9009 eligible images from 4357 patients with CAD were collected. The artificial intelligence (AI) algorithm based on the MMSE achieved an area under the curve (AUC) of 0.832 (95% CI 0.800 to 0.863) in the test group and 0.776 (95% CI 0.730 to 0.821) in the validation group. The AI algorithm based on the MoCA achieved an AUC of 0.764 (95% CI 0.742 to 0.785) in the test group and 0.725 (95% CI 0.701 to 0.750) in the validation group. The calibration curves of the internal test sets of the two models exhibited a good calibration effect. The results of decision curves revealed extensive clinical application value.
Conclusion: The AI algorithm trained on fundus images in this study exerted promising performance in screening MCI in the CAD population and might be a non-invasive and effective alternative for early diagnosis of the disease.
期刊介绍：
Heart is an international peer reviewed journal that keeps cardiologists up to date with important research advances in cardiovascular disease. New scientific developments are highlighted in editorials and put in context with concise review articles. There is one free Editor’s Choice article in each issue, with open access options available to authors for all articles. Education in Heart articles provide a comprehensive, continuously updated, cardiology curriculum.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
