文献速递冠心病外科

人工智能心电图年龄对冠脉搭桥患者风险分层

Risk stratification of coronary artery bypass patients using an artificial intelligence electrocardiogram-derived age.
PubMed 文献 · J Thorac Cardiovasc Surg · 2025-07-18

研究利用13,808例孤立冠脉搭桥患者的术前心电图,以卷积神经网络计算人工智能心电图年龄并定义年龄差。年龄差超过5年者合并症更多、术后并发症风险更高,长期生存更差,提示人工智能心电图年龄可用于风险分层。

要点

  • 年龄差超过5年者术后房颤、延长通气、输血及住院时间风险更高。
  • 年龄差超过5年与长期生存降低独立相关(HR 1.4,95%CI 1.2-1.5)。
  • 人工智能心电图年龄可辅助识别生理年龄偏高的冠脉搭桥患者。

核心结论

  • 年龄差较大可识别出合并症更多、生理年龄更高的冠脉搭桥患者。
  • 人工智能心电图识别的生理年龄偏高与术后结局更差及长期死亡风险升高独立相关。

研究设计与样本

  • 回顾性队列研究,纳入13,808例接受孤立冠脉搭桥手术的患者。
  • 使用术前30天内的心电图,通过卷积神经网络计算人工智能心电图年龄。
  • 年龄差定义为人工智能心电图年龄减实际年龄,并分析其与基线合并症、手术结局及长期生存的关联。

主要发现

  • 实际年龄中位数68(60-74)岁,人工智能心电图年龄67(61-72)岁,平均年龄差-1±8岁(范围-39至+35岁)。
  • 44%的患者人工智能心电图年龄大于实际年龄(正年龄差6±5岁),21.4%的患者年龄差超过5年。
  • 年龄差超过5年者更常见肾衰竭、充血性心力衰竭、心肌梗死史、更高体重指数和更低射血分数。
  • 年龄差超过5年者术后房颤风险更高(OR 1.15,95%CI 1.05-1.30,P=.042)。
  • 年龄差超过5年者术后延长通气风险更高(OR 1.2,95%CI 1.1-1.5,P=.047)。

临床怎么用

  • 术前可考虑用人工智能心电图年龄辅助识别冠脉搭桥高危患者。
  • 对年龄差超过5年者,应加强术后房颤、通气、输血及肾功能监测。

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: The study objective was to assess the prognostic value of artificial intelligence electrocardiogram-derived age in predicting outcomes after isolated coronary artery bypass grafting. METHODS: We used preoperative electrocardiograms (within 30 days from surgery) from 13,808 isolated patients undergoing coronary artery bypass surgery to calculate artificial intelligence electrocardiography-derived age using convolutional neural networks. The age gap was calculated as artificial intelligence electrocardiography-derived age minus chronological age. The associations of age gap with baseline comorbidities, operative outcomes, and long-term survival were analyzed using multivariable regression models. RESULTS: The median chronological age was 68 (60-74) years, and the artificial intelligence electrocardiography-derived age was 67 (61-72) years. Mean age gap was -1 ± 8 years (range, -39 to +35 years). In 44% of patients, the artificial intelligence electrocardiography-derived age was older than the chronological age (positive age gap of 6 (±5) years), and in 21.4% this gap was more than 5 years. Patients with an age gap more than 5 years were more likely to have renal failure, congestive heart failure, a history of myocardial infarction, higher body mass index, and lower ejection fraction. Postoperatively, they were at higher risk of atrial fibrillation (odds ratio, 1.15; 95% CI, 1.05-1.30; P = .042), prolonged ventilation (odds ratio, 1.2; 95% CI, 1.1-1.5; P = .047), blood transfusion (odds ratio, 1.15; 95% CI, 1.1-1.30; P = .017), postoperative creatinine (B-coefficient +0.15 units, P < .001), and hospital stay (B-coefficient +0.7 days, P = .001). Long-term survival was lower in patients with an age gap more than 5 years compared with those with an age gap 5 years or less (hazard ratio, 1.4; 95% CI, 1.2-1.5; P < .001). CONCLUSIONS: Higher age gap identifies a cohort of patients undergoing coronary artery bypass grafting with increased comorbidities and advanced physiological age. Advanced physiological age identified by artificial intelligence electrocardiography is independently associated with worse operative outcomes and long-term mortality.

来源:J Thorac Cardiovasc Surg,查看原文。版权归原作者所有。

引用

  1. Sawma T, Arghami A, Schaff HV, et al. Risk stratification of coronary artery bypass patients using an artificial intelligence electrocardiogram-derived age. J Thorac Cardiovasc Surg. 2025. PMID: 40684845. doi:10.1016/j.jtcvs.2025.06.037

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。