Osaka University Institute for Datability Science, Suita, Japan.
Department of Ophthalmology, Osaka University Medical School, Suita, Japan.
BMJ Open. 2024 Oct 8;14(10):e078609. doi: 10.1136/bmjopen-2023-078609.
Despite extensive exploration of potential biomarkers of cardiovascular diseases (CVDs) derived from retinal images, it remains unclear how retinal images contribute to CVD risk profiling and how the results can inform lifestyle modifications. Therefore, we aimed to determine the performance of cardiovascular risk prediction model from retinal images via explicitly estimating 10 traditional CVD risk factors and compared with the model based on actual risk measurements.
A prospective cohort study design.
The UK Biobank (UKBB), a prospective cohort study, following the health conditions including CVD outcomes of adults recruited between 2006 and 2010.
A subset of data from the UKBB which contains 52 297 entries with retinal images and 5-year cumulative incidence of major adverse cardiovascular events (MACE) was used. Our dataset is split into 3:1:1 as training set (n=31 403), validation set (n=10 420) and testing set (n=10 474). We developed a deep learning (DL) model to predict 5-year MACE using a two-stage DL neural network.
We computed accuracy, area under the receiver operating characteristic curve (AUC) and compared variations in the risk prediction models combining CVD risk factors and retinal images.
The first-stage DL model demonstrated that the 10 CVD risk factors can be estimated from a given retinal image with an accuracy ranging between 65.2% and 89.8% (overall AUC of 0.738 with 95% CI: 0.710 to 0.766). In MACE prediction, our model outperformed the traditional score-based models, with 8.2% higher AUC than Systematic COronary Risk Evaluation (SCORE), 3.5% for SCORE 2 and 7.1% for the Framingham Risk Score (with p value<0.05 for all three comparisons).
Our algorithm estimates the 5-year risk of MACE based on retinal images, while explicitly presenting which risk factors should be checked and intervened. This two-stage approach provides human interpretable information between stages, which helps clinicians gain insights into the screening process copiloting with the DL model.
尽管已经广泛探索了源自视网膜图像的心血管疾病（CVD）潜在生物标志物，但仍不清楚视网膜图像如何有助于 CVD 风险分析，以及结果如何为生活方式改变提供信息。因此，我们旨在通过明确估计 10 种传统 CVD 风险因素来确定基于视网膜图像的心血管风险预测模型的性能，并与基于实际风险测量的模型进行比较。
前瞻性队列研究设计。
英国生物库（UKBB）是一项前瞻性队列研究，跟踪包括 CVD 结局在内的成年人的健康状况，参与者于 2006 年至 2010 年期间招募。
使用 UKBB 的一个子集数据，其中包含 52297 个条目，包括视网膜图像和 5 年累积主要不良心血管事件（MACE）发生率。我们的数据集分为 3:1:1 作为训练集（n=31403）、验证集（n=10420）和测试集（n=10474）。我们开发了一种深度学习（DL）模型，使用两阶段 DL 神经网络来预测 5 年 MACE。
我们计算了准确性、接收器工作特征曲线下的面积（AUC），并比较了结合 CVD 风险因素和视网膜图像的风险预测模型的变化。
第一阶段 DL 模型表明，从给定的视网膜图像中可以以 65.2%至 89.8%的准确度估计 10 种 CVD 风险因素（整体 AUC 为 0.738，95%CI：0.710 至 0.766）。在 MACE 预测中，我们的模型优于传统的基于评分的模型，AUC 比系统性冠状动脉风险评估（SCORE）高 8.2%，比 SCORE 2 高 3.5%，比 Framingham 风险评分高 7.1%（所有三个比较均具有统计学意义）。
我们的算法基于视网膜图像估计 5 年 MACE 风险，同时明确显示应检查和干预哪些风险因素。这种两阶段方法在各阶段之间提供了人类可解释的信息，有助于临床医生在与 DL 模型合作的筛查过程中获得深入了解。
