基于视网膜眼底图像的深度学习模型预测ACS患者远期不良心血管事件
本研究为多中心诊断性研究,纳入4 703例急性冠脉综合征患者,采集视网膜眼底图像并随访主要不良心脑血管事件。研究构建以Inception-Resnet-V2为核心的多模态深度学习模型,在开发集和外部测试集评估预测性能。结果显示模型具有一定预测能力,类激活映射提示模型决策时聚焦于视网膜血管区域。
要点
- 基于视网膜眼底图像的模型在开发集预测MACCE的AUC为0.709。
- 模型在外部测试集预测MACCE的AUC为0.644,风险分层能力稳健。
- 类激活映射显示模型决策时聚焦于视网膜血管区域。
核心结论
- 基于视网膜眼底图像的深度学习模型能够有效预测ACS患者远期不良心血管事件风险,具有风险分层能力与临床可解释性,有望成为无创风险评估工具。
研究设计与样本
- 多中心诊断性研究,2021年7月至2023年7月在北京安贞医院、北京大兴医院、北京密云医院和海南医科大学第二附属医院纳入ACS患者。
- 共纳入4 703例ACS患者,中位年龄59岁,男性3 504例(74.51%),开发集1 521例,外部测试集3 182例。
- 采集视网膜眼底图像,以Inception-Resnet-V2为核心构建多模态深度学习模型,主要终点为MACCE。
主要发现
- 最长随访时间883天,开发集MACCE发生率为27.42%(417/1 521),外部测试集为10.03%(319/3 182)。
- 模型预测MACCE的AUC在开发集为0.709(95%CI 0.676~0.742),在外部测试集为0.644(95%CI 0.613~0.675)。
- Kaplan-Meier生存曲线显示,开发集和外部测试集高危组MACCE发生率均高于低危组(Plog-rank均<0.05)。
- 类激活映射分析显示模型进行决策时聚焦于视网膜血管区域。
关键数值与推荐
- 开发集模型预测MACCE的AUC为0.709(95%CI 0.676~0.742)。
- 外部测试集模型预测MACCE的AUC为0.644(95%CI 0.613~0.675)。
临床怎么用
- 基于视网膜眼底图像的深度学习模型可作为ACS患者无创风险评估的辅助工具。
- 依据ROC曲线最佳截断值可将ACS患者分为低危组和高危组,高危组MACCE发生率更高。
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
Objective: To develop and validate a deep learning model based on retinal fundus images for predicting the risk of long-term adverse cardiovascular events in patients with acute coronary syndrome (ACS). Methods: This multicenter diagnostic study enrolled ACS patients from July 2021 to July 2023 at Beijing Anzhen Hospital, Beijing Daxing Hospital, Beijing Miyun Hospital, and the Second Affiliated Hospital of Hainan Medical University. Retinal fundus images were acquired. Patients underwent follow-up, with the primary endpoint defined as major adverse cardiovascular and cerebrovascular events (MACCE). Patients were divided into a development set and an external test set. A multimodal deep learning model based on Inception-Resnet-V2 was constructed. Predictive performance for MACCE was evaluated using the area under the receiver operating characteristic curve (AUC). Patients were further stratified into low-and high-risk groups according to the optimal cutoff value derived from the receiver operating characteristic curve, and Kaplan-Meier survival curves were generated. Class activation mapping was used to analyze the retinal regions the model focused on during decision-making. Results: A total of 4 703 ACS patients were included, with a median age of 59 years and 3 504 (74.51%) males. The development set comprised 1 521 patients, and the external validation set included 3 182 patients. The maximum follow-up duration was 883 days. The MACCE incidence rate was 27.42% (417/1 521) in the development cohort and 10.03% (319/3 182) in the external validation cohort. The model's AUC for predicting MACCE was 0.709 (95%CI 0.676-0.742) in the development cohort and 0.644 (95%CI 0.613-0.675) in the external validation cohort. Kaplan-Meier survival curves demonstrated that the MACCE incidence was higher in the high-risk group than in the low-risk group in both the development and external validation cohorts (P<0.05 for log-rank tests). Class activation mapping analysis revealed that the model focused on retinal vascular regions during decision-making. Conclusions: A deep learning model based on retinal fundus images effectively predicts long-term adverse cardiovascular event risk in ACS patients, demonstrating robust risk stratification capability and clinical interpretability. It holds promise as a noninvasive risk assessment tool. 目的: 开发并验证一款基于视网膜眼底图像的深度学习模型,用于预测急性冠脉综合征(ACS)患者远期不良心血管事件的风险。 方法: 本研究为多中心诊断性研究。自2021年7月至2023年7月于首都医科大学附属北京安贞医院、北京大兴医院、北京密云医院和海南医科大学第二附属医院纳入ACS患者,采集其视网膜眼底图像。对入选患者进行随访,主要终点为主要不良心脑血管事件(MACCE)。将患者分为开发集和外部测试集,构建以Inception-Resnet-V2为核心的多模态深度学习模型,通过受试者工作特征曲线下面积(AUC)及Kaplan-Meier生存曲线(依据受试者工作特征曲线获得的最佳截断值将患者分为低危组和高危组)评估模型对MACCE的预测性能。利用类激活映射分析模型进行决策时所关注的视网膜区域。 结果: 共纳入4 703例ACS患者,中位年龄59岁,男性3 504例(74.51%)。开发集1 521例,外部测试集3 182例。最长随访时间883 d。开发集中MACCE发生率27.42%(417/1 521);外部测试集为10.03%(319/3 182)。模型在开发集中预测MACCE的AUC为0.709(95%CI 0.676~0.742),在外部测试集中AUC为0.644(95%CI 0.613~0.675)。Kaplan-Meier生存曲线显示,开发集和外部测试集中,高危组的MACCE发生率均高于低危组(Plog-rank均<0.05)。类激活映射分析结果显示模型决策时聚焦于视网膜血管区域。 结论: 基于视网膜眼底图像的深度学习模型能够有效预测ACS患者的远期不良心血管事件风险,具有稳健的风险分层能力与临床可解释性,有望成为一种无创的风险评估工具。.
引用
- Ding, Feng, Han, et al. [Development of a deep learning model for predicting adverse cardiovascular events in patients with acute coronary syndrome based on retinal fundus images]. Zhonghua Xin Xue Guan Bing Za Zhi. 2026. PMID: 41688180. doi:10.3760/cma.j.cn112148-20251009-00704
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。