School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, 310023, Zhejiang, China.
Key Laboratory of Biomedical Intelligent Computing Technology of Zhejiang Province, Hangzhou, 310023, Zhejiang, China.
Sci Rep. 2024 Oct 7;14(1):23278. doi: 10.1038/s41598-024-73176-3.
Coronary artery disease (CAD) is one of the most common cardiovascular disorders affecting millions of individuals globally. It is the leading cause of mortality in both the wealthy and impoverished nations. CAD patients exhibit a wide range of symptoms, some of which are not evident until a major incident occurs. The development of techniques for early detection and precise diagnosis is heavily dependent on research. The proposed system introduces a novel approach, Generative Adversarial Networks Augmented Naïve Bayes (GAN-ANB), to classify high-risk CAD patients using Coronary Computed Tomography Angiography (CCTA) imaging data. The database included images from Coronary Computed Tomography Angiography (CCTA) records of 5,000 individuals. The developed GAN framework consists of a generator to generate synthetic patient profiles, and a discriminator to distinguish between genuine and synthetic profiles to improve the identification of high-risk CAD patients. Adding synthetic data to the training process allowed the discriminator to be utilized further to improve predictive modeling. The performance of the GAN-enhanced prediction model was assessed using accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic curve (ROC). The model exhibited an outstanding Dice Similarity Coefficient (0.91), Mean Intersection Over Union (0.90), recall (0.96), and precision (0.98) in differentiating between high-risk and low-risk individuals. The identification of high-risk patients with CAD is greatly enhanced by the integration of GANs with clinical and imaging data. ROC of 0.99 was achieved by the GAN-ANB model, which outperformed conventional machine learning models, was achieved using the GAN-ANB model. High cholesterol level, diabetes, and some CCTA-derived imaging characteristics, including plaque load and luminal stenosis, were among the major predictors. This method offers a powerful tool for early diagnosis and intervention, potentially leading to improved patient outcomes and lower healthcare expenditure.
冠状动脉疾病（CAD）是影响全球数百万人的最常见心血管疾病之一。它是富裕和贫困国家死亡的主要原因。CAD 患者表现出多种症状，其中一些直到重大事件发生才显现出来。早期检测和精确诊断技术的发展在很大程度上依赖于研究。所提出的系统引入了一种新方法，即生成对抗网络增强朴素贝叶斯（GAN-ANB），使用冠状动脉计算机断层血管造影（CCTA）成像数据对高危 CAD 患者进行分类。该数据库包括来自冠状动脉计算机断层血管造影（CCTA）记录的 5000 个人的图像。所开发的 GAN 框架包括一个生成器，用于生成合成患者资料，以及一个鉴别器，用于区分真实和合成资料，以提高高危 CAD 患者的识别能力。在训练过程中添加合成数据，使得鉴别器可以进一步用于改善预测模型。使用准确性、敏感性、特异性和接收者操作特征曲线（ROC）下的面积来评估 GAN 增强预测模型的性能。该模型在区分高危和低危个体方面表现出出色的 Dice 相似系数（0.91）、平均交集重叠（0.90）、召回率（0.96）和精度（0.98）。通过将 GAN 与临床和成像数据集成，极大地提高了对 CAD 高危患者的识别能力。GAN-ANB 模型实现了 0.99 的 ROC，优于传统机器学习模型。高胆固醇水平、糖尿病和一些 CCTA 衍生的成像特征，包括斑块负荷和管腔狭窄，是主要的预测因素之一。该方法为早期诊断和干预提供了强大的工具，可能会改善患者的预后并降低医疗保健支出。
