One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA.
Harvard Medical School, Boston, MA, USA.
Nat Commun. 2024 Mar 21;15(1):2536. doi: 10.1038/s41467-024-45733-x.
Anthracyclines can cause cancer therapy-related cardiac dysfunction (CTRCD) that adversely affects prognosis. Despite guideline recommendations, only half of the patients undergo surveillance echocardiograms. An AI model detecting reduced left ventricular ejection fraction from 12-lead electrocardiograms (ECG) (AI-EF model) suggests ECG features reflect left ventricular pathophysiology. We hypothesized that AI could predict CTRCD from baseline ECG, leveraging the AI-EF model's insights, and developed the AI-CTRCD model using transfer learning on the AI-EF model. In 1011 anthracycline-treated patients, 8.7% experienced CTRCD. High AI-CTRCD scores indicated elevated CTRCD risk (hazard ratio (HR), 2.66; 95% CI 1.73-4.10; log-rank p < 0.001). This remained consistent after adjusting for risk factors (adjusted HR, 2.57; 95% CI 1.62-4.10; p < 0.001). AI-CTRCD score enhanced prediction beyond known factors (time-dependent AUC for 2 years: 0.78 with AI-CTRCD score vs. 0.74 without; p = 0.005). In conclusion, the AI model robustly stratified CTRCD risk from baseline ECG.
蒽环类药物可引起癌症治疗相关的心脏功能障碍（CTRCD），从而对预后产生不利影响。尽管有指南建议，但只有一半的患者接受了超声心动图监测。一种能够从 12 导联心电图（ECG）中检测到左心室射血分数降低的人工智能模型（AI-EF 模型）表明，心电图特征反映了左心室的病理生理学。我们假设 AI 可以通过基线 ECG 预测 CTRCD，利用 AI-EF 模型的见解，并通过在 AI-EF 模型上进行迁移学习来开发 AI-CTRCD 模型。在 1011 名接受蒽环类药物治疗的患者中，8.7%的患者出现了 CTRCD。高 AI-CTRCD 评分表明 CTRCD 风险增加（风险比 (HR)，2.66；95%置信区间 1.73-4.10；对数秩检验 p<0.001）。在调整了风险因素后，这一结果仍然一致（调整后的 HR，2.57；95%置信区间 1.62-4.10；p<0.001）。AI-CTRCD 评分在已知因素之外增强了预测能力（2 年时间的 AUC：有 AI-CTRCD 评分时为 0.78，无 AI-CTRCD 评分时为 0.74；p=0.005）。总之，该 AI 模型能够从基线 ECG 中可靠地分层 CTRCD 风险。
