Citations

AbstractAims The Food and Drug Administration (FDA) approval of the Watchman device [percutaneous left atrial appendage occlusion (LAAO)] has resulted in the widespread use of this procedure in many centres across the USA. We sought to estimate the nationwide utilization and frequency of adverse outcomes associated with Watchman device implantation. The objective of this study was to evaluate the Watchman device implantation peri-procedural complications and comparison of the results with the previous studies.Methods and results The National Inpatient Sample (NIS) was queried for all hospitalizations with a primary diagnosis of atrial fibrillation or atrial flutter during the year 2016 with percutaneous LAAO during the same admission (ICD-10 code—02L73DK). The frequency of peri-procedural complications, including mortality, procedure-related stroke, major bleeding requiring blood transfusion, and pericardial effusion, was assessed. We compared the complication rates with the published randomized controlled trials and the European Watchman registry. An estimated 5175 LAAO procedures were performed in 2016. The majority of procedures was performed in males (59.1%), age ≥75 years (58.7%), and White (83.1%). The overall complication rate was 1.9%. The in-hospital mortality was 0.29%. Pericardial effusion requiring pericardiocentesis was the most frequent complication (0.68%). Bleeding requiring transfusion was noted in 0.1% of device implants. The rates of post-procedure stroke and systemic embolism were 0% and 0.29%, respectively.Conclusion Percutaneous LAAO with the Watchman device in the USA is associated with low in-hospital complications and a similar safety profile to a recently published EWOLUTION cohort. The complication rates were lower than those reported in the major randomized clinical trials (RCTs). We report the frequency of peri-procedural complications of the LAAO using the Watchman device from the NIS database. We also compare the frequency of peri-procedural complications with the previously published RCTs and EWOLUTION cohort. Our findings are in concordance with findings from EWOLUTION cohort and compare favourably with RCTs.

AbstractBackgroundMagnetic resonance imaging (MRI) in patients with legacy cardiovascular implantable electronic devices (CIEDs) in situ is likely underutilized. We hypothesized the clinical benefit of MRI would outweigh the risks in legacy CIED patients.MethodsThis is a single‐center retrospective study that evaluated and classified the utility of MRI using a prospectively maintained database. The outcomes were classified as aiding in diagnosis, treatment, or both for the patients attributable to the MRI. We then assessed the incidence of adverse effects (AE) when the MRI was performed.ResultsIn 668, MRIs performed on 479 patients, only 13 (1.9%) MRIs did not aid in the diagnosis or treatment of the patient. Power‐on reset events without clinical sequelae in three scans (0.45%) were the only AE. The probability of an adverse event happening without any benefit from the MRI scan was 1.1 × 10−4. A maximum benefit in diagnosis using MRI was obtained in ruling out space‐occupying lesions (121/185 scans, 65.4%). Scans performed in patients for elucidating answers to queries in treatment were most frequently done for disease staging at long term follow‐up (167/470 scans, 35.5%). Conservative treatment (184/470 scans, 39%) followed by medication changes (153/470 scans, 28.7%) were the most common treatment decisions made.ConclusionsThe utility of MRI in patients with non‐MRI‐conditional CIEDs far outweighs the risk of adverse events when imaging is done in the context of a multidisciplinary program that oversees patient safety.

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.

AbstractObjectiveThis study sought to determine if single‐chamber operation and/or loss of rate response (RR) during elective replacement indicator (ERI) in patients with dual‐chamber pacemakers lead to increased symptom burden, healthcare utilization, and atrial fibrillation (AF).BackgroundDual‐chamber pacemakers often change from dual‐ to single‐chamber pacing mode and/or lose RR functionality at ERI to preserve battery. Single‐chamber pacing increases the incidence of heart failure, AF, and pacemaker syndrome suggesting these changes may be deleterious.MethodsA retrospective analysis of 700 patients was completed. Three comparisons were analyzed: Comparison 1: mode change and RR loss versus no change; Comparison 2: RR loss only versus no change; Comparison 3: mode change only versus no change (in patients with no RR programmed at baseline).ResultsIn Comparison 1, 121 (46%) patients with setting changes experienced symptoms (most often dyspnea and fatigue/exercise intolerance) versus 3 (4%) without setting changes (p < .0001). Similar results were noted in Comparisons 2 and 3 (p = .0016 and p = .0001, respectively). In Comparison 1, patients with setting change sought provider contact more than patients without setting changes (p = .0001). A significant difference was not noted in Comparison 2 or 3. Overall 14 (2%) patients were hospitalized, all of whom had setting changes.ConclusionsSetting changes at ERI including a change from dual‐ to single‐chamber pacing and/or loss of RR results in a significantly increased symptom burden and increased healthcare utilization.

AbstractIntroductionVenous stenosis is a well‐recognized complication of transvenous leads (TVLs) that is encountered during lead revisions or device upgrades. We here report the outcomes of TVL placement facilitated by fibroplasty or tunneling (TUN) procedure.MethodsWe conducted a single‐center retrospective cohort study of all patients undergoing TVL implantation requiring fibroplasty or TUN from 2005 to 2017. Medical records and procedure reports were reviewed for relevant data. Outcomes for fibroplasty and TUN to facilitate TVL placement were compared.ResultsSixty patients had fibroplasty and thirty‐five patients had a TUN procedure. There was no difference in procedure success rates between the two groups (97% fibroplasty vs. 100% TUN; p = .98). The fluoroscopy time was longer (fibroplasty = 39.7 ± 21.5 min vs. TUN = 29.2 ± 21.3 min; p = .01) and the total procedural time was shorter in the fibroplasty group (fibroplasty = 247 ± 77.8 min vs. TUN = 287 ± 77.1 min; p = .01). TUN was associated with a significantly higher incidence of acute complications (fibroplasty = 0 vs. TUN = 8; p = .002) most requiring invasive intervention and/or transfusion with blood products. Long‐term complications requiring additional device‐related procedures were comparable between the two groups (fibroplasty = 6 vs. TUN = 6; logrank p = .21).ConclusionsFor patients with venous stenosis requiring additional TVL, balloon fibroplasty is associated with similar rates of success and a significantly decreased incidence of acute complications when compared with subcutaneous TUN.

Artificial intelligence (AI) and machine learning (ML) in medicine are currently areas of intense exploration, showing potential to automate human tasks and even perform tasks beyond human capabilities. Literacy and understanding of AI/ML methods are becoming increasingly important to researchers and clinicians. The first objective of this review is to provide the novice reader with literacy of AI/ML methods and provide a foundation for how one might conduct an ML study. We provide a technical overview of some of the most commonly used terms, techniques, and challenges in AI/ML studies, with reference to recent studies in cardiac electrophysiology to illustrate key points. The second objective of this review is to use examples from recent literature to discuss how AI and ML are changing clinical practice and research in cardiac electrophysiology, with emphasis on disease detection and diagnosis, prediction of patient outcomes, and novel characterization of disease. The final objective is to highlight important considerations and challenges for appropriate validation, adoption, and deployment of AI technologies into clinical practice.

e17535 Background: Androgen Deprivation Therapy (ADT) is commonly used to treat prostate cancer (PC), but has been associated with cardiac morbidity and mortality. The exact mechanisms of this association are unclear. We sought to use an artificial intelligence (AI) enabled algorithm to identify ECG changes in PC patients who received ADT compared to PC patients who did not receive ADT. Methods: From 1,000,000 ECGs performed on 210,414 patients between 1993 and 2017 at our institution, a convolutional neural network was developed to detect predictive signatures for cardiac pathologies. During this process, the ability to predict “estimated sex” of the patient was developed, with output values ranging from 0 (female) to 1 (male). We applied this algorithm to 8,619 ECGs performed on 1,057 men age 75 or younger treated with radiation for high-risk or recurrent PC at our institution, and compared estimated sex after receiving ADT (n = 1,065) to ADT-naive ECGs (n = 7,554). We correlated ECG-identified estimated sex with serum testosterone levels using Spearman rank correlation. Results: Patients who had received ADT had a mean (SD) estimated sex value of 0.81 (0.26) compared to 0.92 (0.17) for those who did not (p < 0.001). Difference between estimated sex in post-ADT ECGs and ADT-naive ECGs remained significant across age groups (Table). Decreased serum total testosterone correlated with decreased estimated sex values in men receiving ADT (R = .57, p < 0.001). Conclusions: ADT for prostate cancer is associated with changes in AI-identified ECG parameters, including lower estimated male sex after receiving ADT. Lower ECG male sex estimate was associated with decreased serum testosterone. In this study, we provide preliminary proof of concept for a potential non-invasive means of monitoring treatment effect and physiologic change using ECGs. [Table: see text]

AbstractQTc interval prolongation can lead to life‐threatening complications such as Torsade de Pointes (TdP), ventricular tachycardia (VT) and sudden cardiac death (SCD). It can occur with tyrosine kinase inhibitors (TKIs) but comparative real‐world analyses on the incidence and complication rates are scarce. We retrospectively reviewed all cancer patients treated with TKI therapy at Mayo Clinic between January 2005 and December 2018 and had at least two ECGs (before and after TKI). For each TKI type, we determined the administration rate and incidence of QTc prolongation. QTc prolongation was defined as a corrected QT interval (by Fridericia formula) ≥450 ms in men and ≥470 ms in women. A total of 618 cancer patients were included with 902 TKI administrations, of which 654 (72.5%) were accounted for by pazopanib, sunitinib, imatinib, nilotinib and dasatinib. QTc prolongation (any grade) was reported in 28.8%, most commonly with nilotinib (38.7%) and dasatinib (41.7%). A QTc interval ≥500 ms and a QTc increase ≥60 ms was documented in 46 and 63 administrations, respectively. Life‐threatening toxicity was seen in 14 cases (5.4% of QTc prolongation cases) including VT in 9, SCD in 3 and TdP in two administrations. The response to QTc prolongation was: discontinuation in 68%, dose reduction in 13.5%, temporary hold in 8.1% and no action in 10.4%. In conclusion, QTc prolongation with TKI therapy is very common (∼1/3 of cases) and in 5% (1.7% overall) associated with life‐threatening complications. These data support recommendations for careful ECG monitoring in cancer patients undergoing TKI therapy.

Background: Deep learning algorithms derived in homogeneous populations may be poorly generalizable and have the potential to reflect, perpetuate, and even exacerbate racial/ethnic disparities in health and health care. In this study, we aimed to (1) assess whether the performance of a deep learning algorithm designed to detect low left ventricular ejection fraction using the 12-lead ECG varies by race/ethnicity and to (2) determine whether its performance is determined by the derivation population or by racial variation in the ECG. Methods: We performed a retrospective cohort analysis that included 97 829 patients with paired ECGs and echocardiograms. We tested the model performance by race/ethnicity for convolutional neural network designed to identify patients with a left ventricular ejection fraction ≤35% from the 12-lead ECG. Results: The convolutional neural network that was previously derived in a homogeneous population (derivation cohort, n=44 959; 96.2% non-Hispanic white) demonstrated consistent performance to detect low left ventricular ejection fraction across a range of racial/ethnic subgroups in a separate testing cohort (n=52 870): non-Hispanic white (n=44 524; area under the curve [AUC], 0.931), Asian (n=557; AUC, 0.961), black/African American (n=651; AUC, 0.937), Hispanic/Latino (n=331; AUC, 0.937), and American Indian/Native Alaskan (n=223; AUC, 0.938). In secondary analyses, a separate neural network was able to discern racial subgroup category (black/African American [AUC, 0.84], and white, non-Hispanic [AUC, 0.76] in a 5-class classifier), and a network trained only in non-Hispanic whites from the original derivation cohort performed similarly well across a range of racial/ethnic subgroups in the testing cohort with an AUC of at least 0.930 in all racial/ethnic subgroups. Conclusions: Our study demonstrates that while ECG characteristics vary by race, this did not impact the ability of a convolutional neural network to predict low left ventricular ejection fraction from the ECG. We recommend reporting of performance among diverse ethnic, racial, age, and sex groups for all new artificial intelligence tools to ensure responsible use of artificial intelligence in medicine.