基于视网膜图像的深度学习在冠心病人群中检测轻度认知障碍
本研究为单中心横断面研究,纳入2021年7月至2023年7月北京安贞医院4357例冠心病患者(至少一支血管狭窄≥50%),共9009张眼底图像,训练卷积神经网络模型以MMSE<27和MoCA<26为参考标准检测轻度认知障碍。基于MMSE的模型在测试组AUC为0.832(95%CI 0.800-0.863),验证组为0.776(95%CI 0.730-0.821);基于MoCA的模型测试组AUC为0.764(95%CI 0.742-0.785),验证组为0.725(95%CI 0.701-0.750)。结论认为该AI算法在冠心病人群中筛查MCI表现良好,可能成为无创有效的早期诊断替代工具。
要点
- 基于眼底图像的深度学习模型可在冠心病人群中辅助筛查轻度认知障碍。
- 以MMSE为参考的模型测试组AUC为0.832,外部验证组为0.776。
- 模型校准曲线良好,决策曲线显示广泛临床适用价值。
核心结论
- 基于眼底图像训练的AI算法在冠心病人群中筛查轻度认知障碍表现出良好性能,可能成为无创且有效的早期诊断替代方法。
研究设计与样本
- 单中心横断面研究,纳入2021年7月至2023年7月北京安贞医院冠心病患者(至少一支血管狭窄≥50%)。
- 2021年7月至2023年5月符合条件的患者按8:2随机分为模型训练集和内测试集,2023年6月至7月入组患者为外部验证组。
- 使用四种卷积神经网络架构训练受试者眼底图像,参考标准分别为MMSE评分<27和MoCA评分<26,并通过模型集成建立综合视觉MCI检测模型。
- 共收集4357例冠心病患者的9009张合格图像。
主要发现
- 基于MMSE的AI算法在测试组AUC为0.832(95%CI 0.800-0.863),在验证组AUC为0.776(95%CI 0.730-0.821)。
- 基于MoCA的AI算法在测试组AUC为0.764(95%CI 0.742-0.785),在验证组AUC为0.725(95%CI 0.701-0.750)。
- 两个模型内测试集的校准曲线显示良好校准效果。
- 决策曲线分析结果显示广泛的临床适用价值。
关键数值与推荐
- MCI参考标准:MMSE评分<27或MoCA评分<26。
- 冠心病入组标准:至少一支血管狭窄≥50%。
临床怎么用
- 在冠心病人群中,可考虑利用眼底图像深度学习模型作为轻度认知障碍的无创筛查辅助工具,辅助早期识别与干预。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
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. TRIAL REGISTRATION NUMBER: NCT06102226.
引用
- Ye Y, Feng W, Ding Y, et al. Retinal image-based deep learning for mild cognitive impairment detection in coronary artery disease population. Heart. 2025. PMID: 40379470. doi:10.1136/heartjnl-2024-325486
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。