Yamani, Mohamad H.

Abstract Aims Cardiovascular disease is a major threat to maternal health, with cardiomyopathy being among the most common acquired cardiovascular diseases during pregnancy and the postpartum period. The aim of our study was to evaluate the effectiveness of an electrocardiogram (ECG)-based deep learning model in identifying cardiomyopathy during pregnancy and the postpartum period. Methods and results We used an ECG-based deep learning model to detect cardiomyopathy in a cohort of women who were pregnant or in the postpartum period seen at Mayo Clinic. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. We compared the diagnostic probabilities of the deep learning model with natriuretic peptides and a multivariable model consisting of demographic and clinical parameters. The study cohort included 1807 women; 7%, 10%, and 13% had left ventricular ejection fraction (LVEF) of 35% or less, <45%, and <50%, respectively. The ECG-based deep learning model identified cardiomyopathy with AUCs of 0.92 (LVEF ≤ 35%), 0.89 (LVEF < 45%), and 0.87 (LVEF < 50%). For LVEF of 35% or less, AUC was higher in Black (0.95) and Hispanic (0.98) women compared to White (0.91). Natriuretic peptides and the multivariable model had AUCs of 0.85 to 0.86 and 0.72, respectively. Conclusions An ECG-based deep learning model effectively identifies cardiomyopathy during pregnancy and the postpartum period and outperforms natriuretic peptides and traditional clinical parameters with the potential to become a powerful initial screening tool for cardiomyopathy in the obstetric care setting.

e13002 Background: Despite improvement in survival in breast cancer patients from advanced therapies, rates of chemotherapy-induced cardiotoxicity manifesting as a decline in left ventricular ejection fraction (LVEF) have offset some of these benefits in patients receiving anthracycline-based chemotherapy followed by trastuzumab. Results suggesting clinical biomarkers predict cardiotoxicity are inconsistent. Recently, expression of angiotensin II type 1 receptor (ATR1) and endothelin 1 (ET1) has shown to play a role in breast tumor growth. We sought to evaluate whether the presence of ATR1 and ET1 in breast cancer tissue using immunohistochemistry (IHC) and qRT-PCR can predict chemotherapy-induced cardiotoxicity. Methods: We hypothesized that elevated expression of ATR1 and ET1 in tumor tissue is associated with chemotherapy-induced cardiotoxicity (LVEF < 50%) compared to tissue from controls. Preliminarily, 34 paraffin-embedded breast tissue specimens from women with breast cancer treated with anthracycline-based chemotherapy and trastuzumab were retrieved for analysis. IHC and qRT-PCR for expression of ATR1 and ET1 was performed on all specimens. Results: We found that ET1 expression was significantly increased in patients with an LVEF < 50%. In addition, we noted the lower the LVEF, the higher the ET1 expression (p = 0.03). We also found patients with a change in LVEF of greater than 10% had more ET1 expression compared to those without a change in LVEF (p = 0.05). We did not find a significant relationship between ATR1 and LVEF. Conclusions: Increased ET1 expression in breast tumor tissue may predict cardiotoxicity. Our findings may aid in future research using novel biomarkers to predict breast cancer patients at risk for developing chemotherapy-induced cardiotoxicity. In addition, targeted therapies to these biomarkers may potentially help prevent the development of cardiotoxicity.