Oikonomou Evangelos K, Sangha Veer, Dhingra Lovedeep S, Aminorroaya Arya, Coppi Andreas, Krumholz Harlan M, Baldassarre Lauren A, Khera Rohan
Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT.
Department of Engineering Science, University of Oxford, Oxford, UK.
medRxiv. 2024 Mar 19:2024.03.12.24304047. doi: 10.1101/2024.03.12.24304047.
Risk stratification strategies for cancer therapeutics-related cardiac dysfunction (CTRCD) rely on serial monitoring by specialized imaging, limiting their scalability.
To examine an artificial intelligence (AI)-enhanced electrocardiographic (AI-ECG) surrogate for imaging risk biomarkers, and its association with CTRCD.
Across a five-hospital U.S.-based health system (2013-2023), we identified patients with breast cancer or non-Hodgkin lymphoma (NHL) who received anthracyclines (AC) and/or trastuzumab (TZM), and a control cohort receiving immune checkpoint inhibitors (ICI). We deployed a validated AI model of left ventricular systolic dysfunction (LVSD) to ECG images (≥0.1, positive screen) and explored its association with i) global longitudinal strain (GLS) measured within 15 days (=7,271 pairs); ii) future CTRCD (new cardiomyopathy, heart failure, or left ventricular ejection fraction [LVEF]<50%), and LVEF<40%. In the ICI cohort we correlated baseline AI-ECG-LVSD predictions with downstream myocarditis.
Higher AI-ECG LVSD predictions were associated with worse GLS (-18% [IQR:-20 to -17%] for predictions<0.1, to -12% [IQR:-15 to -9%] for ≥0.5 (<0.001)). In 1,308 patients receiving AC/TZM (age 59 [IQR:49-67] years, 999 [76.4%] women, 80 [IQR:42-115] follow-up months) a positive baseline AI-ECG LVSD screen was associated with ~2-fold and ~4.8-fold increase in the incidence of the composite CTRCD endpoint (adj.HR 2.22 [95%CI:1.63-3.02]), and LVEF<40% (adj.HR 4.76 [95%CI:2.62-8.66]), respectively. Among 2,056 patients receiving ICI (age 65 [IQR:57-73] years, 913 [44.4%] women, follow-up 63 [IQR:28-99] months) AI-ECG predictions were not associated with ICI myocarditis (adj.HR 1.36 [95%CI:0.47-3.93]).
AI applied to baseline ECG images can stratify the risk of CTRCD associated with anthracycline or trastuzumab exposure.
癌症治疗相关心脏功能障碍（CTRCD）的风险分层策略依赖于通过专业成像进行连续监测，这限制了它们的可扩展性。
研究一种用于成像风险生物标志物的人工智能（AI）增强心电图（AI-ECG）替代指标及其与CTRCD的关联。
在美国一个五家医院的医疗系统（2013 - 2023年）中，我们确定了接受蒽环类药物（AC）和/或曲妥珠单抗（TZM）的乳腺癌或非霍奇金淋巴瘤（NHL）患者，以及接受免疫检查点抑制剂（ICI）的对照队列。我们将经过验证的左心室收缩功能障碍（LVSD）AI模型应用于心电图图像（≥0.1，阳性筛查），并探讨其与以下方面的关联：i）在15天内测量的整体纵向应变（GLS）（=7271对）；ii）未来的CTRCD（新发心肌病、心力衰竭或左心室射血分数[LVEF]<50%），以及LVEF<40%。在ICI队列中，我们将基线AI-ECG-LVSD预测与下游心肌炎进行关联。
AI-ECG LVSD预测值越高，与越差的GLS相关（预测值<0.1时为-18%[四分位间距：-20%至-17%]，≥0.5时为-12%[四分位间距：-15%至-9%]（<0.001））。在1308例接受AC/TZM的患者中（年龄59岁[四分位间距：49 - 67岁]，999例[76.4%]为女性，随访80个月[四分位间距：42 - 115个月]），基线AI-ECG LVSD筛查阳性与复合CTRCD终点事件发生率增加约2倍和约4.8倍相关（调整后风险比2.22[95%置信区间：1.63 - 3.02]），以及LVEF<40%（调整后风险比4.76[95%置信区间：2.62 - 8.66]）。在2056例接受ICI的患者中（年龄65岁[四分位间距：57 - 73岁]，913例[44.4%]为女性，随访63个月[四分位间距：28 - 99个月]），AI-ECG预测与ICI心肌炎无关（调整后风险比1.36[95%置信区间：0.47 - 3.93]）。
应用于基线心电图图像的AI可以对与蒽环类药物或曲妥珠单抗暴露相关的CTRCD风险进行分层。
