Friedman, Paul A.

Introduction: Cardiac veins serve as substrate for arrhythmogenesis, and are especially involved as foci in atrial fibrillation. Understanding cardiac vein anatomy along with myocardial extension into these structures can improve electrophysiological mapping and electrical isolation of arrhythmogenic substrate. Accurately defining cardiac vein anatomy is critical in improving success of ablation therapy for atrial fibrillation. Methods: We performed measurements on 620 formalin-fixed autopsy hearts explanted from October 1998 to July 2003. The integrity of the thoracic veins and their cardiac connections were examined and systematic measurements of the superior and inferior vena cavae, azygous vein, vein of Marshall, coronary sinus, and pulmonary veins were performed and data were analyzed using univariate statistics. Results: We found that muscular extensions into the pulmonary veins were visible in 99% of the examined hearts, and were circumferential around the vein ostia (99.6%). Muscle extension into the SVC was found in 78% of examined hearts. These extensions were largely circumferential around the ostium (39%), but were also found to be asymmetric in a majority of hearts. Asymmetry was found in hearts with longer muscle extensions; no symmetry was observed in extensions greater than 0.8cm. Muscle extensions into the IVC were not seen. Occasionally, macroscopic muscle extensions into the azygous vein were visible (6%). The vein of Marshall was found to be patent to probing in the majority of hearts examined (72%) and was almost always overlying the lateral left atrial endocardial ridge. Conclusions: Our data suggest that all pulmonary veins need to be electrically isolated during atrial fibrillation ablation because of the almost universal presence of myocardial tissue extending into the veins. Mapping of the SVC should be done circumferentially and if potentials are noted isolation should also be performed. The IVC did not have muscle extensions and is unlikely to be a site of arrhythmogenesis. The azygous vein occasionally had muscle extensions and thus requires mapping and possible isolation. The vein of Marshall can be a substrate for arrhythmogenesis and is accessible for ablation by targeting the lateral left atrial endocardial ridge.

Device infection is associated with increased mortality in cardiovascular implantable electronic device (CIED) recipients. However, published data regarding clinical predictors of mortality in patients with CIED infection are limited. In current investigation, we sought to identify patient and device-related factors associated with mortality in CIED infection cases. We performed a retrospective review of all cases of CIED infection admitted to Mayo Clinic Rochester from 1991 to 2008. Survival data were obtained from hospital medical records and United Sates Social Security Index. Key data regarding patient demographics, device features, comorbid conditions, clinical presentation, echocardiographic findings and management strategies were abstracted. Potential risk factors for short (30-day) and long-term mortality were analyzed using univariate and multivariable logistic and Cox proportional hazards regression models, respectively. 415 cases of CIED infection were identified from the institutional database. The mean duration of follow-up for the 243 patients who were alive at last follow-up was 6.9 years. In multivariable model, congestive heart failure (CHF, Odds ratio 9.31, 95% CI 2.08-41.67), chronic corticosteroid use (OR 4.04, 1.40-11.60) and presentation with CIED-related infective endocarditis (CIED-IE), (OR 5.6, 2.25-13.92) were associated with increased odds of short-term mortality. Independent predictors of long-term mortality on multivariable model included patients' age (hazard ratio for 10-year increase 1.2, 95% CI 1.06-1.36), CHF (HR 2.01, 1.42-2.86), metastatic malignancy (HR 5.99, 1.67-21.53), corticosteroid use (HR 1.97, 1.22-3.18), renal failure (HR 1.94, 1.37-2.74) and CIED-IE (HR 1.68, 1.17-2.41). Our investigation provides some novel insights into predictors of short- and long-term mortality in CIED infection cases. While comorbid conditions and immunocompromised host status were primary determinants of both short- and long-term mortality, complicated device infection (CIED-IE) is the only predictor that presents an opportunity for intervention where mortality may be reduced by early diagnosis and expedited device removal.

Abstract Aims Mobile devices such as smartphones and watches can now record single-lead electrocardiograms (ECGs), making wearables a potential screening tool for cardiac and wellness monitoring outside of healthcare settings. Because friends and family often share their smart phones and devices, confirmation that a sample is from a given patient is important before it is added to the electronic health record. Methods and results We sought to determine whether the application of Siamese neural network would permit the diagnostic ECG sample to serve as both a medical test and biometric identifier. When using similarity scores to discriminate whether a pair of ECGs came from the same patient or different patients, inputs of single-lead and 12-lead medians produced an area under the curve of 0.94 and 0.97, respectively. Conclusion The similar performance of the single-lead and 12-lead configurations underscores the potential use of mobile devices to monitor cardiac health.

Abstract Aims Recently, deep learning artificial intelligence (AI) models have been trained to detect cardiovascular conditions, including hypertrophic cardiomyopathy (HCM), from the 12-lead electrocardiogram (ECG). In this external validation study, we sought to assess the performance of an AI-ECG algorithm for detecting HCM in diverse international cohorts. Methods and results A convolutional neural network-based AI-ECG algorithm was developed previously in a single-centre North American HCM cohort (Mayo Clinic). This algorithm was applied to the raw 12-lead ECG data of patients with HCM and non-HCM controls from three external cohorts (Bern, Switzerland; Oxford, UK; and Seoul, South Korea). The algorithm’s ability to distinguish HCM vs. non-HCM status from the ECG alone was examined. A total of 773 patients with HCM and 3867 non-HCM controls were included across three sites in the merged external validation cohort. The HCM study sample comprised 54.6% East Asian, 43.2% White, and 2.2% Black patients. Median AI-ECG probabilities of HCM were 85% for patients with HCM and 0.3% for controls (P < 0.001). Overall, the AI-ECG algorithm had an area under the receiver operating characteristic curve (AUC) of 0.922 [95% confidence interval (CI) 0.910–0.934], with diagnostic accuracy 86.9%, sensitivity 82.8%, and specificity 87.7% for HCM detection. In age- and sex-matched analysis (case–control ratio 1:2), the AUC was 0.921 (95% CI 0.909–0.934) with accuracy 88.5%, sensitivity 82.8%, and specificity 90.4%. Conclusion The AI-ECG algorithm determined HCM status from the 12-lead ECG with high accuracy in diverse international cohorts, providing evidence for external validity. The value of this algorithm in improving HCM detection in clinical practice and screening settings requires prospective evaluation.

AbstractBackgroundLeft bundle branch block (LBBB) induced cardiomyopathy is an increasingly recognized disease entity. However, no clinical testing has been shown to be able to predict such an occurrence.Case reportA 70‐year‐old male with a prior history of LBBB with preserved ejection fraction (EF) and no other known cardiovascular conditions presented with presyncope, high‐grade AV block, and heart failure with reduced EF (36%). His coronary angiogram was negative for any obstructive disease. No other known etiologies for cardiomyopathy were identified. Artificial intelligence‐enabled ECGs performed 6 years prior to clinical presentation consistently predicted a high probability (up to 91%) of low EF. The patient successfully underwent left bundle branch area (LBBA) pacing with correction of the underlying LBBB. Subsequent AI ECGs showed a large drop in the probability of low EF immediately after LBBA pacing to 47% and then to 3% 2 months post procedure. His heart failure symptoms markedly improved and EF normalized to 54% at the same time.ConclusionsArtificial intelligence‐enabled ECGS may help identify patients who are at risk of developing LBBB‐induced cardiomyopathy and predict the response to LBBA pacing.

Background. Predicting long-term mortality postkidney transplantation (KT) using baseline clinical data presents significant challenges. This study aims to evaluate the predictive power of artificial intelligence (AI)-enabled analysis of preoperative electrocardiograms (ECGs) in forecasting long-term mortality following KT. Methods. We analyzed preoperative ECGs from KT recipients at three Mayo Clinic sites (Minnesota, Florida, and Arizona) between January 1, 2006, and July 30, 2021. The study involved 6 validated AI algorithms, each trained to predict future development of atrial fibrillation, aortic stenosis, low ejection fraction, hypertrophic cardiomyopathy, amyloid heart disease, and biological age. These algorithms’ outputs based on a single preoperative ECG were correlated with patient mortality data. Results. Among 6504 KT recipients included in the study, 1764 (27.1%) died within a median follow-up of 5.7 y (interquartile range: 3.00–9.29 y). All AI-ECG algorithms were independently associated with long-term all-cause mortality (P < 0.001). Notably, few patients had a clinical cardiac diagnosis at the time of transplant, indicating that AI-ECG scores were predictive even in asymptomatic patients. When adjusted for multiple clinical factors such as recipient age, diabetes, and pretransplant dialysis, AI algorithms for atrial fibrillation and aortic stenosis remained independently associated with long-term mortality. These algorithms also improved the C-statistic for predicting overall (C = 0.74) and cardiac-related deaths (C = 0.751). Conclusions. The findings suggest that AI-enabled preoperative ECG analysis can be a valuable tool in predicting long-term mortality following KT and could aid in identifying patients who may benefit from enhanced cardiac monitoring because of increased risk.

Abstract Introduction Transsubclavian venous implantation of the Aveir leadless cardiac pacemaker (LCP) has not been previously reported. Methods and Results Three cases of transsubclavian implantation of the Aveir LCP are reported. Two cases were postbilateral orthotopic lung transplant, without appropriate femoral or jugular access due to recent ECMO cannulation and jugular central venous catheters. In one case, there was strong patient preference for same‐day discharge. Stability testing confirmed adequate fixation and electrical testing confirmed stable parameters in all cases. All patients tolerated the procedure well without significant immediate complications. Conclusions We demonstrate the feasibility of transsubclavian implantation of the Aveir LCP.

Abstract Aims Augmenting echocardiography with artificial intelligence would allow for automated assessment of routine parameters and identification of disease patterns not easily recognized otherwise. View classification is an essential first step before deep learning can be applied to the echocardiogram. Methods and results We trained two- and three-dimensional convolutional neural networks (CNNs) using transthoracic echocardiographic (TTE) studies obtained from 909 patients to classify nine view categories (10 269 videos). Transthoracic echocardiographic studies from 229 patients were used in internal validation (2582 videos). Convolutional neural networks were tested on 100 patients with comprehensive TTE studies (where the two examples chosen by CNNs as most likely to represent a view were evaluated) and 408 patients with five view categories obtained via point-of-care ultrasound (POCUS). The overall accuracy of the two-dimensional CNN was 96.8%, and the averaged area under the curve (AUC) was 0.997 on the comprehensive TTE testing set; these numbers were 98.4% and 0.998, respectively, on the POCUS set. For the three-dimensional CNN, the accuracy and AUC were 96.3% and 0.998 for full TTE studies and 95.0% and 0.996 on POCUS videos, respectively. The positive predictive value, which defined correctly identified predicted views, was higher with two-dimensional rather than three-dimensional networks, exceeding 93% in apical, short-axis aortic valve, and parasternal long-axis left ventricle views. Conclusion An automated view classifier utilizing CNNs was able to classify cardiac views obtained using TTE and POCUS with high accuracy. The view classifier will facilitate the application of deep learning to echocardiography.

Background Recent studies have indicated high rates of future major adverse cardiovascular events in patients with Takotsubo cardiomyopathy (TC), but there is no well‐established tool for risk stratification. This study sought to evaluate the prognostic value of several artificial intelligence‐augmented ECG (AI‐ECG) algorithms in patients with TC. Methods and Results This study examined consecutive patients in the prospective and observational Mayo Clinic Takotsubo syndrome registry. Several previously validated AI‐ECG algorithms were used for the estimation of ECG‐ age, probability of low ejection fraction, and probability of atrial fibrillation. Multivariable models were constructed to evaluate the association of AI‐ECG and other clinical characteristics with major adverse cardiac events, defined as cardiovascular death, recurrence of TC, nonfatal myocardial infarction, hospitalization for congestive heart failure, and stroke. In the final analysis, 305 patients with TC were studied over a median follow‐up of 4.8 years. Patients with future major adverse cardiac events were more likely to be older, have a history of hypertension, congestive heart failure, worse renal function, as well as high‐risk AI‐ECG findings compared with those without. Multivariable Cox proportional hazards analysis indicated that the presence of 2 or 3 high‐risk findings detected by AI‐ECG remained a significant predictor of major adverse cardiac events in patients with TC after adjustment by conventional risk factors (hazard ratio, 4.419 [95% CI, 1.833–10.66], P =0.001). Conclusions The combined use of AI‐ECG algorithms derived from a single 12‐lead ECG might detect subtle underlying patterns associated with worse outcomes in patients with TC. This approach might be beneficial for stratifying high‐risk patients with TC.