Citations

Atrial fibrillation (AF) is one of the most common cardiac arrhythmias. Implantable and wearable cardiac devices have enabled the detection of asymptomatic AF episodes—termed subclinical AF (SCAF). SCAF, the prevalence of which is likely significantly underestimated, is associated with increased cardiovascular and all-cause mortality and a significant stroke risk. Recent advances in machine learning, namely artificial intelligence–enabled ECG (AI-ECG), have enabled identification of patients at higher likelihood of SCAF. Leveraging the capabilities of AI-ECG algorithms to drive screening protocols could eventually allow for earlier detection and treatment and help reduce the burden associated with AF.

Abstract Background Cardiovascular disease (CVD) has been identified as a major threat to maternal health in the US and UK with cardiomyopathy being one of the most common acquired CVD in the pregnant and postpartum period. Diagnosing cardiomyopathy in pregnancy is challenging due to an overlap of cardiovascular symptoms with normal pregnancy symptoms. Purpose The purpose of this study was to evaluate the effectiveness of an ECG based deep learning model in identifying cardiomyopathy among pregnant and postpartum women. Methods We utilized an ECG based deep learning model to detect cardiomyopathy in a cohort of pregnant or postpartum women seen at multiple hospital sites. Model performance was evaluated using area under the 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. Results 1,807 women were included. 7%, 10% and 13% had LVEF ≤35%, <45% and <50% respectively. The ECG based deep learning model identified cardiomyopathy with an AUC of 0.92 for left ventricular ejection fraction (LVEF) ≤35%, 0.89 for LVEF <45% and 0.87 for LVEF <50%. For LVEF ≤35%, 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 and 0.72 respectively. Conclusions A deep learning model effectively identifies cardiomyopathy in pregnant or postpartum women, outperforms natriuretic peptides and traditional clinical parameters with the potential to become a powerful initial screening tool for cardiomyopathy in the obstetric care setting. Funding Acknowledgement Type of funding sources: Other. Main funding source(s): This study was made possible using resources supported by the Mayo Clinic Women's Health Research Center and the Mayo Clinic Building Interdisciplinary Research Careers in Women's Health (BIRCWH) Program funded by the National Institutes of Health (NIH), grant number K12 HD065987. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

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.

Introduction: Percutaneous left atrial appendage closure is well established as an alternative to anticoagulation therapy for stroke prophylaxis among patients with non-valvular atrial fibrillation (NVAF) with relative or absolute contraindications to anticoagulation. Only the Watchman® (BSC) device has FDA approval for this indication. There are no current guidelines on the choice of short term antithrombotic therapy following placement of the Watchman® device. The landmark Watchman® clinical trials utilized warfarin and aspirin in the first 45 days to facilitate endothelialization; however these studies were started prior to direct oral anticoagulants (DOAC) becoming widely available. Our main objective was to compare bleeding outcomes with warfarin vs. DOACs following Watchman® device placement. Methods: We conducted a retrospective chart review of all patients who received a Watchman® device at all three Mayo Clinic sites (MN, FL, AZ) between January 2010 and December 2018 with follow up for outcomes at 45 days or 6 weeks following procedure. We conducted bivariate analysis using t-tests and chi-square tests as appropriate. A logistic regression model was constructed to evaluate the effect of anticoagulant choice on bleeding and thromboembolic outcomes. Clinically significant bleeding was defined as bleeding leading to interruption of anticoagulation regimen or requiring transfusion. Results: 232 patients were identified (33% female), mean age in years, CHADS2VASC score and HASBLED scores were 77, 5 and 4 respectively. Overall, 39% were initiated on non-warfarin therapies and 11% had a significant bleeding episode during follow up. There was no difference in clinically significant bleeding events (11% vs. 12%; OR 0.92, 95% CI: 0.32 – 2.65) with short term DOAC use compared to warfarin. Patients who received a Watchman® due to GI bleeding were more likely to have a bleeding event in the first 6 weeks following Watchman® (OR: 4.08, 95% CI: 1.30 – 12.75). Conclusion: This observational study demonstrates no significant difference in bleeding episodes with DOACs compared to warfarin during the first 6 weeks following Watchman® device placement in patients at high risk for bleeding. Larger prospective studies are needed.

AbstractBackgroundChange in left atrial pressure (LAP) has been shown to be associated with symptom improvement post‐MitraClip; however, the association between acute procedural changes in transmitral diastolic mean gradient (MG) compared to LAP and symptom improvement is not well established.Methods164 consecutive patients undergoing MitraClip at Mayo Clinic between June 2014 and May 2018 were included. Preclip and postclip MG and LAP were recorded. Baseline demographics, clinical, and echocardiographic outcomes, including 30‐day New York Heart Association (NYHA) functional status were obtained from patient charts.ResultsMedian age was 81.5 years (IQR: 76.3, 87), 34% were female and 94.5% had NYHA class III and IV functional status at baseline. At baseline, median MG was 4 mmHg (IQR: 3, 5) and LAP was 19 mmHg (IQR: 16, 23.5). Following MitraClip deployment, the median MG was 4 mmHg (IQR: 3, 6) and the median LAP was 17 mmHg (IQR: 14, 21), 69.5% of patients had less than moderate MR. There was no statistically significant association between change in MG and NYHA functional class at 30 days (OR = 0.95, 95% CI: 0.76–1.20). However, a reduction in LAP following MitraClip deployment was significantly associated with improvement in NYHA functional status at 30 days following adjustments for age and sex (aOR 3.36, 95% CI: 1.34–8.65). There was no significant correlation between change in mean LAP and change in MG (p = .98).ConclusionUnlike change in left atrial pressure, change in MG post‐MitraClip was not associated with patient reported outcomes at 30 days and did not correlate with change in left atrial pressure. Long‐term follow up is needed to evaluate the impact of LA pressure on symptoms.

Background: Identification of systolic heart failure among patients presenting to the emergency department (ED) with acute dyspnea is challenging. The reasons for dyspnea are often multifactorial. A focused physical evaluation and diagnostic testing can lack sensitivity and specificity. The objective of this study was to assess the accuracy of an artificial intelligence-enabled ECG to identify patients presenting with dyspnea who have left ventricular systolic dysfunction (LVSD). Methods: We retrospectively applied a validated artificial intelligence-enabled ECG algorithm for the identification of LVSD (defined as LV ejection fraction ≤35%) to a cohort of patients aged ≥18 years who were evaluated in the ED at a Mayo Clinic site with dyspnea. Patients were included if they had at least one standard 12-lead ECG acquired on the date of the ED visit and an echocardiogram performed within 30 days of presentation. Patients with prior LVSD were excluded. We assessed the model performance using area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity. Results: A total of 1606 patients were included. Median time from ECG to echocardiogram was 1 day (Q1: 1, Q3: 2). The artificial intelligence-enabled ECG algorithm identified LVSD with an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.86–0.91) and accuracy of 85.9%. Sensitivity, specificity, negative predictive value, and positive predictive value were 74%, 87%, 97%, and 40%, respectively. To identify an ejection fraction <50%, the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were 0.85 (95% CI, 0.83–0.88), 86%, 63%, and 91%, respectively. NT-proBNP (N-terminal pro-B-type natriuretic peptide) alone at a cutoff of >800 identified LVSD with an area under the receiver operating characteristic curve of 0.80 (95% CI, 0.76–0.84). Conclusions: The ECG is an inexpensive, ubiquitous, painless test which can be quickly obtained in the ED. It effectively identifies LVSD in selected patients presenting to the ED with dyspnea when analyzed with artificial intelligence and outperforms NT-proBNP. Graphic Abstract: A graphic abstract is available for this article.