Predicting CT-Based Coronary Artery Disease Using Vascular Biomarkers Derived from Fundus Photographs with a Graph Convolutional Neural Network

Abstract

The study population contains 145 patients who were prospectively recruited for coronary CT angiography (CCTA) and fundoscopy. This study first examined the association between retinal vascular changes and the Coronary Artery Disease Reporting and Data System (CAD-RADS) as assessed on CCTA. Then, we developed a graph neural network (GNN) model for predicting the CAD-RADS as a proxy for coronary artery disease. The CCTA scans were stratified by CAD-RADS scores by expert readers, and the vascular biomarkers were extracted from their fundus images. Association analyses of CAD-RADS scores were performed with patient characteristics, retinal diseases, and quantitative vascular biomarkers. Finally, a GNN model was constructed for the task of predicting the CAD-RADS score compared to traditional machine learning (ML) models. The experimental results showed that a few retinal vascular biomarkers were significantly associated with adverse CAD-RADS scores, which were mainly pertaining to arterial width, arterial angle, venous angle, and fractal dimensions. Additionally, the GNN model achieved a sensitivity, specificity, accuracy and area under the curve of 0.711, 0.697, 0.704 and 0.739, respectively. This performance outperformed the same evaluation metrics obtained from the traditional ML models (p < 0.05). The data suggested that retinal vasculature could be a potential biomarker for atherosclerosis in the coronary artery and that the GNN model could be utilized for accurate prediction.

DeepChestGNN: A Comprehensive Framework for Enhanced Lung Disease Identification through Advanced Graphical Deep Features

“…The sensitivity, precision, F1-Score, and accuracy metrics were evaluated for each model. In contrast, existing models like NSCGCN [17], PNA-GCN [9], ResGNet-C [65], Efficient-B4-FPN [66], and GraphSAGE [67] demonstrate lower accuracy levels ranging from 63.83% to 98.04%. The highest accuracy was achieved by NSCGCN [17] at 98.04% and by PNA-GCN [9] at 97.79%, demonstrating the second-highest accuracy.…”

“…The highest accuracy was achieved by NSCGCN [17] at 98.04% and by PNA-GCN [9] at 97.79%, demonstrating the second-highest accuracy. GraphSAGE [67] achieved the lowest accuracy at 63.83% in the classification results. Notably, DeepChestGNN outperforms other models with exceptional metrics: sensitivity of 98.72%, precision of 98.71%, F1-Score of 98.71%, and an impressive accuracy of 99.74%.…”

Use of artificial intelligence on retinal images to accurately predict the risk of cardiovascular event (CVD-AI)

“…Traditionally, most existing algorithms simply measure success in terms of detection accuracy, where the CVD risk is calculated by conventional equations. For instance, [27, 28, 49, 50] report the outcomes of their algorithms in terms of AUC, regarding successful models as those that have an AUC > 0.70. Although this approach has its merits merely knowing that a model can predict CVD risk with an AUC > 0.70 is of limited value because simply achieving a high level of accuracy does not necessarily mean that the algorithm has learnt what was expected.…”

Cardiac Healthcare Digital Twins Supported by Artificial Intelligence-Based Algorithms and Extended Reality—A Systematic Review

“…This is a combination of 3D CNNs AND LSTM. Fan Huang et al [145] focused on predicting coronary artery disease (CAD) from CT scans using vascular biomarkers derived from fundus photographs through a GNN. This method showed that specific retinal vascular biomarkers, such as arterial width and fractal dimensions, were significantly associated with adverse CAD-RADS scores.…”