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 (E.K.O., V.S., L.S.D., A.A., H.M.K., L.A.B., R.K.), Yale School of Medicine, New Haven, CT.
Department of Engineering Science, University of Oxford, United Kingdom (V.S.).
Circ Cardiovasc Qual Outcomes. 2025 Jan;18(1):e011504. doi: 10.1161/CIRCOUTCOMES.124.011504. Epub 2024 Sep 2.
Risk stratification strategies for cancer therapeutics-related cardiac dysfunction (CTRCD) rely on serial monitoring by specialized imaging, limiting their scalability. We aimed to examine an application of artificial intelligence (AI) to ECG images as a surrogate for imaging risk biomarkers and its association with early CTRCD.
Across a US-based health system (2013-2023), we identified 1550 patients (aged, 60 [interquartile range, 51-69] years, 1223 [78.9%] women) without cardiomyopathy who received anthracyclines or trastuzumab for breast cancer or non-Hodgkin lymphoma and had ECG performed ≤12 months before treatment. We deployed a validated AI model of left ventricular systolic dysfunction to baseline ECG images and defined low-, intermediate-, and high-risk groups based on AI-ECG left ventricular systolic dysfunction probabilities of <0.01, 0.01 to 0.1, and ≥0.1 (positive screen), respectively. We explored the association with early CTRCD (new cardiomyopathy, heart failure, or left ventricular ejection fraction <50%), or left ventricular ejection fraction <40%, up to 12 months after treatment. In a mechanistic analysis, we assessed the association between global longitudinal strain and AI-ECG left ventricular systolic dysfunction probabilities in studies performed within 15 days of each other.
Among 1550 patients without known cardiomyopathy (median follow-up, 14.1 [interquartile range, 13.4-17.1] months), 83 (5.4%), 562 (36.3%), and 905 (58.4%) were classified as high, intermediate, and low risk, respectively, by baseline AI-ECG. A high-risk versus low-risk AI-ECG screen (≥0.1 versus <0.01) was associated with a 3.4-fold and 13.5-fold higher incidence of CTRCD (adjusted hazard ratio, 3.35 [95% CI, 2.25-4.99]) and left ventricular ejection fraction <40% (adjusted hazard ratio, 13.52 [95% CI, 5.06-36.10]), respectively. Post hoc analyses supported longitudinal increases in AI-ECG probabilities within 6 to 12 months of a CTRCD event. Among 1428 temporally linked echocardiograms and ECGs, AI-ECG left ventricular systolic dysfunction probabilities were associated with worse global longitudinal strain (global longitudinal strain, -19% [interquartile range, -21% to -17%] for probabilities <0.1, to -15% [interquartile range, -15% to -9%] for ≥0.5 [<0.001]).
AI applied to baseline ECG images can stratify the risk of early CTRCD associated with anthracycline or trastuzumab exposure in the setting of breast cancer and non-Hodgkin lymphoma therapy.
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。我们旨在研究人工智能（AI）在心电图图像中的应用，以此作为成像风险生物标志物的替代指标，并探讨其与早期CTRCD的关联。
在美国的一个医疗系统（2013 - 2023年）中，我们确定了1550例无心肌病的患者（年龄60岁[四分位间距，51 - 69岁]，1223例[78.9%]为女性），这些患者因乳腺癌或非霍奇金淋巴瘤接受了蒽环类药物或曲妥珠单抗治疗，且在治疗前≤12个月进行了心电图检查。我们将经过验证的左心室收缩功能障碍AI模型应用于基线心电图图像，并根据AI - ECG左心室收缩功能障碍概率分别<0.01、0.01至0.1和≥0.1（阳性筛查）定义低、中、高风险组。我们探讨了其与治疗后长达12个月的早期CTRCD（新发心肌病、心力衰竭或左心室射血分数<50%）或左心室射血分数<40%的关联。在一项机制分析中，我们评估了在彼此间隔15天内进行的研究中，整体纵向应变与AI - ECG左心室收缩功能障碍概率之间的关联。
在1550例无已知心肌病的患者中（中位随访时间，14.1[四分位间距，13.4 - 17.1]个月），根据基线AI - ECG，分别有83例（5.4%）、562例（36.3%）和905例（58.4%）被分类为高、中、低风险。高风险与低风险AI - ECG筛查（≥0.1对<0.01）分别与CTRCD发生率高3.4倍和13.5倍（调整后风险比，3.35[95%CI，2.25 - 4.99]）以及左心室射血分数<40%（调整后风险比，13.52[95%CI，5.06 - 36.10]）相关。事后分析支持在CTRCD事件发生后的6至12个月内AI - ECG概率的纵向增加。在1428例时间上相关的超声心动图和心电图中，AI - ECG左心室收缩功能障碍概率与较差的整体纵向应变相关（整体纵向应变，概率<0.1时为-19%[四分位间距，-21%至-17%]，≥0.5时为-15%[四分位间距，-15%至-9%][<0.001]）。
应用于基线心电图图像的AI可以对乳腺癌和非霍奇金淋巴瘤治疗中与蒽环类药物或曲妥珠单抗暴露相关的早期CTRCD风险进行分层。
