Development and Multinational Validation of an Ensemble Deep Learning Algorithm for Detecting and Predicting Structural Heart Disease Using Noisy Single-lead Electrocardiograms.

Background and Aims: AI-enhanced 12-lead ECG can detect a range of structural heart diseases (SHDs) but has a limited role in community-based screening. We developed and externally validated a noise-resilient single-lead AI-ECG algorithm that can detect SHD and predict the risk of their development using wearable/portable devices. Methods: Using 266,740 ECGs from 99,205 patients with paired echocardiographic data at Yale New Haven Hospital, we developed ADAPT-HEART, a noise-resilient, deep-learning algorithm, to detect SHD using lead I ECG. SHD was defined as a composite of LVEF<40%, moderate or severe left-sided valvular disease, and severe LVH. ADAPT-HEART was validated in four community hospitals in the US, and the population-based cohort of ELSA-Brasil. We assessed the model's performance as a predictive biomarker among those without baseline SHD across hospital-based sites and the UK Biobank. Results: The development population had a median age of 66 [IQR, 54-77] years and included 49,947 (50.3%) women, with 18,896 (19.0%) having any SHD. ADAPT-HEART had an AUROC of 0.879 (95% CI, 0.870-0.888) with good calibration for detecting SHD in the test set, and consistent performance in hospital-based external sites (AUROC: 0.852-0.891) and ELSA-Brasil (AUROC: 0.859). Among those without baseline SHD, high vs. low ADAPT-HEART probability conferred a 2.8- to 5.7-fold increase in the risk of future SHD across data sources (all P<0.05). Conclusions: We propose a novel model that detects and predicts a range of SHDs from noisy single-lead ECGs obtainable on portable/wearable devices, providing a scalable strategy for community-based screening and risk stratification for SHD.

An Ensemble Deep Learning Algorithm for Structural Heart Disease Screening Using Electrocardiographic Images: PRESENT SHD.

Background: Identifying structural heart diseases (SHDs) early can change the course of the disease, but their diagnosis requires cardiac imaging, which is limited in accessibility. Objective: To leverage 12-lead ECG images for automated detection and prediction of multiple SHDs using a novel deep learning model. Methods: We developed a series of convolutional neural network models for detecting a range of individual SHDs from images of ECGs with SHDs defined by transthoracic echocardiograms (TTEs) performed within 30 days of the ECG at the Yale New Haven Hospital (YNHH). SHDs were defined based on TTEs with LV ejection fraction <40%, moderate-to-severe left-sided valvular disease (aortic/mitral stenosis or regurgitation), or severe left ventricular hypertrophy (IVSd > 1.5cm and diastolic dysfunction). We developed an ensemble XGBoost model, PRESENT-SHD, as a composite screen across all SHDs. We validated PRESENT-SHD at 4 US hospitals and a prospective population-based cohort study, the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), with concurrent protocolized ECGs and TTEs. We also used PRESENT-SHD for risk stratification of new-onset SHD or heart failure (HF) in clinical cohorts and the population-based UK Biobank (UKB). Results: The models were developed using 261,228 ECGs from 93,693 YNHH patients and evaluated on a single ECG from 11,023 individuals at YNHH (19% with SHD), 44,591 across external hospitals (20-27% with SHD), and 3,014 in the ELSA-Brasil (3% with SHD). In the held-out test set, PRESENT-SHD demonstrated an AUROC of 0.886 (0.877-894), sensitivity of 89%, and specificity of 66%. At hospital-based sites, PRESENT-SHD had AUROCs ranging from 0.854-0.900, with sensitivities and specificities of 93-96% and 51-56%, respectively. The model generalized well to ELSA-Brasil (AUROC, 0.853 [0.811-0.897], sensitivity 88%, specificity 62%). PRESENT-SHD performance was consistent across demographic subgroups. A positive PRESENT-SHD screen portended a 2- to 4-fold higher risk of new-onset SHD/HF, independent of demographics, comorbidities, and the competing risk of death across clinical sites and UKB, with high predictive discrimination. Conclusion: We developed and validated PRESENT-SHD, an AI-ECG tool identifying a range of SHD using images of 12-lead ECGs, representing a robust, scalable, and accessible modality for automated SHD screening and risk stratification.

Sigmoid ventricular septum treated with endocardial ablation to improve left ventricular outflow: cases report.

Background: Sigmoid Ventricular Septum (SVS) is a type of hypertrophic cardiomyopathy characterized by a reduced angle between the basal interventricular septum and the ascending aorta, and SVS can lead to dynamic Left Ventricular Outflow Tract obstruction (LVOTO) during hypercontractile states. Patients experiencing LVOTO may manifest symptoms such as angina, syncope, etc. Radiofrequency ablation (RFA) has been utilized to treat patients with hypertrophic obstructive cardiomyopathy, but there is no reports on its use in treating LVOTO resulting from SVS. Our report describes two cases of SVS treated with endocardial ablation to improve LVOTO. Case report: Case 1: A 74-year-old female patient with angina and syncope was admitted to the hospital and diagnosed with SVS by transthoracic echocardiogram. The patient exhibited LVOTO and Systolic Anterior Motion (SAM) phenomena during the administration of the dobutamine stress test. After RFA was performed, the patient's symptoms significantly improved. Additionally, septum decreased from 16 to 13 mm after ten months, and the morphological changes associated with SVS also disappeared. Case 2: A 57-year-old female was admitted to the hospital due to recurrent chest pain after physical activity for more than four years. The transthoracic echocardiogram indicated that the patient met the diagnostic criteria for SVS, and LVOTO and SAM phenomenaoccurred following dobutamine stress test. The patient had significant improvement in symptoms after undergoing RFA treatment. Conclusions: These two cases represent the first documented instances where dynamic LVOTO caused by SVS could be effectively managed through endocardial RFA.

Impact of Cognitive Impairment on Long-Term Outcomes After Transcatheter Aortic Valve Implantation.

Background: Cognitive impairment assessed using the Mini-Mental Status Examination (MMSE) is associated with short-term mortality after transcatheter aortic valve implantation (TAVI). We assessed the long-term prognostic impact of cognitive impairment in patients with severe aortic stenosis post-TAVI. Methods and Results: We enrolled 1,057 consecutive patients who underwent TAVI at the Kokura Memorial Hospital and prospectively assessed them using the MMSE. Results showed that 319 (30%) patients had cognitive impairment. Compared with normal cognition, cognitive impairment was associated with an increased risk for 5-year all-cause mortality (55% vs. 39%; P<0.001), cardiovascular mortality (23% vs. 14%; P=0.007), and non-cardiovascular mortality (42% vs. 29%; P<0.001). Multivariable analysis showed that cognitive impairment was independently associated with all-cause mortality (adjusted hazard ratio [aHR] 1.37; 95% confidence interval [CI] 1.10-1.70; P=0.005), and this result was consistent regardless of stratification based on age, sex, body mass index, left ventricular ejection fraction and clinical frailty scale without significant interaction. Patients with MMSE scores <16 had a significantly higher mortality rate compared with patients with MMSE scores >25, 21-25, and 16-20, respectively. Conclusions: Cognitive impairment assessed using MMSE scores is independently associated with an increased risk for 5-year all-cause mortality in patients undergoing TAVI.

Novel techniques for quantifying oxygen pulse curve characteristics during cardiopulmonary exercise testing in tetralogy of fallot.

Background: Cardiopulmonary exercise testing (CPET) is used in evaluation of repaired tetralogy of Fallot (rTOF), particularly for pulmonary valve replacement need. Oxygen pulse (O2P) is the CPET surrogate for stroke volume and peripheral oxygen extraction. Objectives: This study assessed O2P curve properties against non-invasive cardiac output monitoring (NICOM) and clinical testing. Methods: This cross-sectional study included 44 rTOF patients and 10 controls. Three new evaluations for O2P curve analysis during CPET were developed. Best fit early and late regression slopes of the O2P curve were used to calculate: 1) the early to late ratio, or "O2 pulse response ratio" (O2PRR); 2) the portion of exercise until slope inflection, or "flattening fraction" (FF); 3) the area under the O2P response curve, or "O2P curve area". Results: rTOF patients (median age 35.2 (27.6-39.4); 61% female) had a lower VO2 max (23.4 vs 45.6 ml/kg/min; p < 0.001) and O2P max (11.5 vs 19.1 ml/beat; p < 0.001) compared to controls. Those with a FF occurring <50% through exercise had a lower peak cardiac index and stroke volume, but not VO2 max, compared to those >50%. FF and O2P curve area significantly correlated with peak cardiac index, stroke volume, left and right ventricular ejection fraction, and right ventricular systolic pressure. Conclusion: CPET remains an integral part in the evaluation of rTOF. We introduce three non-invasive methods to assess exercise hemodynamics using the O2P curve data. These evaluations demonstrated significant correlations with stroke volume, cardiac output, and right ventricular pressure.

A Coronary-Friendly Device Mitigating Risk of Coronary Obstruction in Transcatheter Aortic Valve Replacement.

Purpose: Transcatheter aortic valve replacement (TAVR) induced coronary artery obstruction (CAO) is a rare but devastating complication. Current preventive strategies need additional procedures and may be associated with adverse events. This study aimed to evaluate the early safety and efficacy of stand-alone TAVR using the J-Valve (Jianshi JieCheng Medical Technology Co. Ltd, Shanghai, China) in patients at potential high risk for CAO. Patients and Methods: CAO was defined as coronary ostia obstruction requiring intervention. Patients at potential high risk for CAO were identified retrospectively from 673 consecutive patients who underwent TAVR from January 2015 to July 2021 at Zhongshan Hospital, Fudan University. Procedural results and early outcomes were evaluated according to Valve Academic Research Consortium-3 definitions. Results: A total of 20 consecutive patients (age 72 ± 9 years; 85% female;) were included. The Society of Thoracic Surgeons-Predicted Risk of Mortality was 5% (interquartile range, 4 to 10%). All patients (100%) had at least 2 classical risk factors for CAO by pre-procedural computed tomography analysis, and 90% patients had native aortic valve diseases. TAVR was successful in 95% of cases, with only 1 patient requiring second device implantation. Early safety at 30 days was achieved in all cases without death. All patients were free from CAO, stroke or emergency reintervention. Post-procedural mean aortic valve gradient was 7 (interquartile range, 4, 12) mmHg, and none/trace or mild aortic regurgitation was present in all patients. Conclusion: Stand-alone TAVR using the J-Valve may mitigate the risk of TAVR-induced CAO.

Catheter ablation as first-line treatment for ventricular tachycardia in patients with structural heart disease and preserved left ventricular ejection fraction: a systematic review and meta-analysis.

In this systematic review and meta-analysis, we aim to evaluate the efficacy and safety of catheter ablation as the first-line treatment of ventricular tachycardia (VT) in patients with structural heart disease (SHD) and preserved left ventricular ejection fraction (LVEF). Patients with SHD are particularly susceptible to VT, a condition that increases the risk of sudden cardiac death (SCD). Implantable cardioverter-defibrillators (ICDs) can terminate VT and prevent SCD but do not prevent VT recurrence. The efficacy and safety of CA as a first-line treatment in SHD patients with preserved LVEF remain unclear. We searched PubMed/Medline, EMBASE, Web of Science, and Cochrane CENTRAL for studies reporting the outcomes of CA therapy in patients with VT and preserved LVEF, published up to January 19, 2023. The primary outcome was the incidence of SCD following catheter ablation as the first-line treatment of VT in patients with SHD and preserved LVEF. Secondary outcomes included all-cause mortality, VT recurrence, procedural complications, CA success rate, and ICD implantation after catheter ablation. We included seven studies in the meta-analysis, encompassing a total of 920 patients. The pooled success rate of catheter ablation was 84.6% (95% CI 67.2-93.6). Complications occurred in 6.4% (95% CI 4.0-9.9) of patients, and 13.9% (95% CI 10.1-18.8) required ICD implantation after ablation. VT recurrence was observed in 23.2% (95% CI 14.8-34.6) of patients, while the rate of sudden cardiac death (SCD) was 3.1% (95% CI 1.7-5.6). The overall prevalence of all-cause mortality in this population was 5% (95% CI 1.8-13). CA appears promising as a first-line VT treatment in patients with SHD and preserved LVEF, especially for monomorphic hemodynamically tolerated VT. However, due to the lack of direct comparisons with ICDs and anti-arrhythmic drugs, further research is needed to confirm these findings.

Economic Disparities in Utilization and Outcomes of Structural Heart Disease Interventions in the United States.

Background: Disparities in access to care cause negative health consequences for underserved populations. Economic disparities in structural heart disease (SHD) interventions are not well characterized. Objectives: The objective of this study was to evaluate economic disparities in the utilization and outcomes of SHD interventions in the United States. Methods: We queried the National Inpatient Sample (2016-2020) to examine economic disparities in the utilization, in-hospital outcomes, length of stay, and cost of SHD interventions among patients ≥65 years of age. Outcomes were determined using logistic regression models. Results: A total of 401,005 weighted hospitalizations for transcatheter aortic valve replacement, left atrial appendage occlusion, transcatheter mitral valve repair, and transcatheter mitral valve replacement were included. Utilization rates (number of procedures performed per 100,000 hospitalizations) were higher in patients with high income compared with medium and low income for transcatheter aortic valve replacement (559 vs 456 vs 338), left atrial appendage occlusion (148 vs 136 vs 99), transcatheter mitral valve repair (65 vs 54 vs 41), and transcatheter mitral valve replacement (7.7 vs 6.7 vs 1.2) (all P < 0.01). Low- and medium-income patients had distinctive demographic and clinical risk profiles compared with high-income patients. There were no significant differences in the adjusted in-hospital mortality, key complications, or length of stay between high-, medium-, and low-income patients following any of the 4 SHD interventions. High-income patients incurred a modestly higher cost with any of the 4 SHD interventions compared with medium- and low-income patients. Conclusions: Economic disparities exist in the utilization of SHD interventions in the United States. Nonetheless, adjusted in-hospital outcomes were comparable among high-, medium-, and low-income patients. Multifaceted implementation strategies are needed to attenuate these utilization disparities.

Clinical Advances in Cardiovascular Computed Tomography: From Present Applications to Promising Developments.

PURPOSE OF THE REVIEW: This review aims to provide a profound overview on most recent studies on the clinical significance of Cardiovascular Computed Tomography (CCT) in diagnostic and therapeutic pathways. Herby, this review helps to pave the way for a more extended but yet purposefully use in modern day cardiovascular medicine. RECENT FINDINGS: In recent years, new clinical applications of CCT have emerged. Major applications include the assessment of coronary artery disease and structural heart disease, with corresponding recommendations by major guidelines of international societies. While CCT already allows for a rapid and non-invasive diagnosis, technical improvements enable further in-depth assessments using novel imaging parameters with high temporal and spatial resolution. Those developments facilitate diagnostic and therapeutic decision-making as well as improved prognostication. This review determined that recent advancements in both hardware and software components of CCT allow for highly advanced examinations with little radiation exposure. This particularly strengthens its role in preventive care and coronary artery disease. The addition of functional analyses within and beyond coronary artery disease offers solutions in wide-ranging patient populations. Many techniques still require improvement and validation, however, CCT possesses potential to become a "one-stop-shop" examination.

Perioperative Assessment and Clinical Outcomes of Percutaneous Atrial Septal Defect Closure with Three-Dimensional Transesophageal Echocardiography.

BACKGROUND/OBJECTIVES: To close the atrial septal defect (ASD) with the transcatheter method, correctly defining the defect and selecting the appropriate closure device size are the most critical steps for the procedure's success. Although ASD can be successfully closed under the guidance of three-dimensional (3D) transesophageal echocardiography (TEE) and two-dimensional (2D) TEE, measurement comparisons between different types of defects are still needed. METHODS: Our study was designed retrospectively. Sixty-one patients who underwent transcatheter ASD closure with 2D TEE and 3D TEE between 2020 and 2024 were included. The patients were divided into three groups according to the defect shape: circular, oval, and complex; and the measurement results, perioperative process, and clinical outcomes were compared in each group. RESULTS: The average age of the patients was 35.05 ± 13.87 years, and 41 (67.2%) were women. The average follow-up period of the patients was 15.3 ± 9.18 months. No statistical significance was observed in the comparison of measurements obtained with 3D TEE and 2D TEE in the circular and oval defect groups. The differences between the minimum defect diameters of complex defects measured by 2D TEE and 3D TEE (p: 0.037), IVC rims (p < 0.001), aortic rims (p: 0.012), and the differences between implanted device dimensions and the maximum defect diameters measured by both methods were compared; statistical significance was observed (p: 0.025). CONCLUSIONS: In circular and non-complex oval defects, it has been observed that the size of the closure device selected with 2D TEE or 3D TEE is optimal, and the procedure is practical and feasible. While the closure of complex ASDs with 3D TEE provides reliable and optimal results, using only 2D TEE in complex ASDs may lead to selecting a smaller-sized device.

Left Ventricular Outflow Tract and Transcatheter Mitral Valve Replacement Obstruction and TMVR: Predictors, Evaluation, and Solutions.

In this issue of Structural Heart, high-impact presentations from Transcatheter Valve Therapies 2023 are reviewed. Dr Jaffar Khan provided updates on the current understanding of left ventricular outflow tract obstruction in the field of transcatheter mitral valve replacement, highlighting known predictors of obstruction, a generally agreed-upon strategy for preprocedure assessment, and a host of management strategies in various stages of development and study.

Arrhythmias During Pregnancy: Ventricular Tachycardia in the Setting of Maternal Beta Thalassemia Minor.

Non-sustained ventricular tachycardia (NSVT) poses significant risks during pregnancy, particularly in patients with underlying conditions such as ß-thalassemia. We present a case of a 29-year-old pregnant woman with a history of ß-thalassemia minor who experienced NSVT at 27 weeks gestation. Despite initial concerns for structural heart disease, the workup was unrevealing. Challenges in medication selection and risk assessment were addressed in the context of maternal and fetal well-being. This case underscores the importance of a multidisciplinary approach involving cardiology, obstetrics, and hematology in managing NSVT during pregnancy, emphasizing risk stratification, collaborative decision-making, and long-term follow-up to ensure optimal outcomes for both mother and fetus.

Predictors of permanent pacemaker implantation for transcatheter self-expandable aortic valve implant in the cusp overlap era.

BACKGROUND: Predictors of permanent pacemaker implantation (PPMI) after self-expanding transcatheter aortic valve implant (TAVI) were described. Is unknown if PPMI predictors remain in the era of high implants using the cusp overlap (COP). METHODS: Single-center, prospective, consecutive case series of patients undergoing self-expanding TAVI with the COP approach. The status of PPMI and other clinical events were ascertained at 30 days. RESULTS: A total of 261 patients were included (84% with Evolut, n = 219). Implant depth >4 mm was infrequent (13.8%). TAVI depth (OR 1.259; p = 0.005), first or second-degree auriculo-ventricular block (OR 3.406; p = 0.033), right-bundle (OR 15.477; p < 0.0001), and incomplete left-bundle branch block (OR 7.964; p = 0.036) were found to be independent predictors of PPMI. The risk of PPMI with deep implant and no electrical disturbances was 3%, and 0% with high implant and no prior electrical disturbances. Those who received PPMI had no statistically significant increased risk of death, myocardial infarction, stroke, bleeding events, or vascular complications at 30 days, but longer hospital stay (mean difference 1.43 days more, p = 0.003). CONCLUSIONS: Implant depth and prior conduction abnormalities remain the main predictors of PPMI using self-expanding TAVI in the COP era. Patients with high implants and no prior conduction abnormalities may be candidates for early discharge after uneventful self-expanding TAVI, while the rest may need inpatient monitoring regardless of achieving a high implant. The need for PPMI was associated with longer hospital stays.

Mitral Valve Edge-to-Edge Repair Through an Atrial Septal Shunt Device.

Atrial shunt devices are being implanted with increasing frequency, and there are potential concerns for subsequent procedures using transseptal access. A 79-year-old woman presented with progressive dyspnea of multifactorial etiology with already implanted atrial shunt device. Due to comorbidities, successful mitral-valve edge-to-edge repair was performed transseptally through the shunt device.

Understanding the role of the left atrial appendage on the flow in the atrium.

BACKGROUND: The exclusion/occlusion of the left atrial appendage (LAA) is a treatment option for atrial fibrillation (AF) patients who are at high risk of stroke and high risk of bleeding. As the role of the LAA is not well understood or explored, this study aims to assess its role on flow dynamics in the left atrium. METHODS: Computational fluid dynamics (CFD) simulations were carried out for nine AF patients before and after LAA exclusion. The flow parameters investigated included the LA velocities, Time Averaged Wall Shear Stress (TAWSS), Oscillatory Shear Index (OSI), Relative Residence Time (RRT), and Pressure in the LA. RESULTS: This study shows that, on average, a decrease in TAWSS (1.82 ± 1.85 Pa to 1.27 ± 0.96 Pa, p < 0.05) and a slight increase in OSI (0.16 ± 0.10 to 0.17 ± 0.10, p < 0.05), RRT (1.87 ± 1.84 Pa-1 to 2.11 ± 1.78 Pa-1, p < 0.05), and pressure (-19.2 ± 6.8 mmHg to -15.3 ± 8.3 mmHg, p < 0.05) were observed in the LA after the exclusion of the LAA, with a decrease in low-magnitude velocities. CONCLUSION: The exclusion of the LAA seems to be associated with changes in LA flow dynamics. Further studies are needed to elucidate the clinical implications of these changes.

Cardiac magnetic resonance reveals concealed structural heart disease in patients with frequent premature ventricular contractions and normal echocardiography: A systematic review.

Premature ventricular contractions (PVCs) are a common form of arrhythmic events, often representing an idiopathic and benign condition without further therapeutic interventions. However, in certain circumstances PVCs may represent the epiphenomenon of a concealed structural heart disease (SHD). Surface 12­leads EKG and 24-h dynamic EKG are necessary to assess their main characteristics such as site of origin, frequency and complexity. Echocardiography represents the first-line imaging tool recommended to evaluate cardiac structures and function. Cardiac Magnetic Resonance (CMR) is recognized as a superior modality for detecting structural cardiac alterations, that might evade detection by conventional echocardiography. Moreover, in specific populations such as athletes, CMR may have a crucial role to exclude a concealed SHD and the risk of serious arrhythmic events during sport activity. Some clinical characteristics such as male sex, older age or family history of sudden cardiac death (SCD) or cardiomyopathy, and some electrocardiographic features of PVCs, in particular a right branch bundle block (RBBB) with superior/intermediate axis morphology, the reproducibility of VAs during exercise test (ET) or the evidence of complex ventricular arrhythmias, may warrant a CMR evaluation, due to the high probability of SHD. In this systematic review our objective was to provide an exhaustive overview on the role of CMR in detecting a concealed SHD in patients with high daily burden of PVCs and a normal echocardiographic evaluation, paving the way for a more extensive utilization of CMR in presence of certain high-risk clinical and/or EKG features identified during the diagnostic workup.

Whispers of the Cath lab: "Cases we would rather forget".

In the dynamic field of interventional cardiology, significant strides have been made in reducing periprocedural complications. Echocardiography, particularly transesophageal echocardiography, plays a key role in ensuring the safety and success of structural heart interventions. Its real-time imaging capabilities allow for precise monitoring of device positioning, deployment, and procedural outcomes. By adhering to established imaging protocols and acquiring standard imaging planes, periprocedural echocardiography has become an essential tool for the successful performance of many structural heart interventions. In this manuscript, we present a series of unusual yet significant complications that we encountered during structural interventional procedures in our catheter laboratory. These complications, detected through echocardiography, underscore the critical role of imaging guidance in recognizing, and addressing unforeseen challenges, such as device malposition, thrombus formation in cardiac chambers during structural heart interventions, and cardiac tamponade during transcatheter mitral valve procedures. Through these cases, we highlight the effectiveness of transesophageal echocardiography in promptly identifying complications, allowing for timely intervention and resolution.