PDF(Pubmed)
Abstract：
UNASSIGNED: Atherosclerotic cardiovascular disease (ASCVD) is a leading cause of death globally, and early detection of high-risk individuals is essential for initiating timely interventions. The authors aimed to develop and validate a deep learning (DL) model to predict an individual\'s elevated 10-year ASCVD risk score based on retinal images and limited demographic data.
UNASSIGNED: The study used 89,894 retinal fundus images from 44,176 UK Biobank participants (96% non-Hispanic White, 5% diabetic) to train and test the DL model. The DL model was developed using retinal images plus age, race/ethnicity, and sex at birth to predict an individual\'s 10-year ASCVD risk score using the pooled cohort equation (PCE) as the ground truth. This model was then tested on the US EyePACS 10K dataset (5.8% non-Hispanic White, 99.9% diabetic), composed of 18,900 images from 8969 diabetic individuals. Elevated ASCVD risk was defined as a PCE score of ≥7.5%.
UNASSIGNED: In the UK Biobank internal validation dataset, the DL model achieved an area under the receiver operating characteristic curve of 0.89, sensitivity 84%, and specificity 90%, for detecting individuals with elevated ASCVD risk scores. In the EyePACS 10K and with the addition of a regression-derived diabetes modifier, it achieved sensitivity 94%, specificity 72%, mean error -0.2%, and mean absolute error 3.1%.
UNASSIGNED: This study demonstrates that DL models using retinal images can provide an additional approach to estimating ASCVD risk, as well as the value of applying DL models to different external datasets and opportunities about ASCVD risk assessment in patients living with diabetes.
UNASSIGNED: The study used 89,894 retinal fundus images from 44,176 UK Biobank participants (96% non-Hispanic White, 5% diabetic) to train and test the DL model. The DL model was developed using retinal images plus age, race/ethnicity, and sex at birth to predict an individual\'s 10-year ASCVD risk score using the pooled cohort equation (PCE) as the ground truth. This model was then tested on the US EyePACS 10K dataset (5.8% non-Hispanic White, 99.9% diabetic), composed of 18,900 images from 8969 diabetic individuals. Elevated ASCVD risk was defined as a PCE score of ≥7.5%.
UNASSIGNED: In the UK Biobank internal validation dataset, the DL model achieved an area under the receiver operating characteristic curve of 0.89, sensitivity 84%, and specificity 90%, for detecting individuals with elevated ASCVD risk scores. In the EyePACS 10K and with the addition of a regression-derived diabetes modifier, it achieved sensitivity 94%, specificity 72%, mean error -0.2%, and mean absolute error 3.1%.
UNASSIGNED: This study demonstrates that DL models using retinal images can provide an additional approach to estimating ASCVD risk, as well as the value of applying DL models to different external datasets and opportunities about ASCVD risk assessment in patients living with diabetes.
摘要：
■动脉粥样硬化性心血管疾病（ASCVD）是全球主要的死亡原因，早期发现高危个体对于及时启动干预措施至关重要。作者旨在开发和验证深度学习（DL）模型，以基于视网膜图像和有限的人口统计数据来预测个人的10年ASCVD风险评分。
■该研究使用了来自44,176名英国生物库参与者的89,894张视网膜眼底图像（96％的非西班牙裔白人，5%的糖尿病)对DL模型进行训练和测试。DL模型是使用视网膜图像加上年龄开发的，种族/民族,和出生时的性别，使用合并队列方程（PCE）作为基本事实来预测个体的10年ASCVD风险评分。然后在USEyePACS10K数据集上测试了该模型(5.8%非西班牙裔白人，99.9%糖尿病患者），由8969名糖尿病患者的18,900张图像组成。ASCVD风险升高定义为PCE评分≥7.5%。
■在UKBiobank内部验证数据集中，DL模型实现了接收器工作特性曲线下的面积为0.89，灵敏度84%，特异性90%，用于检测ASCVD风险评分升高的个体。在EyePACS10K中，并添加了回归衍生的糖尿病调节剂，灵敏度达到94%,特异性72%，平均误差-0.2%，平均绝对误差为3.1%。
■这项研究表明，使用视网膜图像的DL模型可以提供一种评估ASCVD风险的额外方法，以及将DL模型应用于不同外部数据集的价值和糖尿病患者ASCVD风险评估的机会。
■该研究使用了来自44,176名英国生物库参与者的89,894张视网膜眼底图像（96％的非西班牙裔白人，5%的糖尿病)对DL模型进行训练和测试。DL模型是使用视网膜图像加上年龄开发的，种族/民族,和出生时的性别，使用合并队列方程（PCE）作为基本事实来预测个体的10年ASCVD风险评分。然后在USEyePACS10K数据集上测试了该模型(5.8%非西班牙裔白人，99.9%糖尿病患者），由8969名糖尿病患者的18,900张图像组成。ASCVD风险升高定义为PCE评分≥7.5%。
■在UKBiobank内部验证数据集中，DL模型实现了接收器工作特性曲线下的面积为0.89，灵敏度84%，特异性90%，用于检测ASCVD风险评分升高的个体。在EyePACS10K中，并添加了回归衍生的糖尿病调节剂，灵敏度达到94%,特异性72%，平均误差-0.2%，平均绝对误差为3.1%。
■这项研究表明，使用视网膜图像的DL模型可以提供一种评估ASCVD风险的额外方法，以及将DL模型应用于不同外部数据集的价值和糖尿病患者ASCVD风险评估的机会。
