Citations

Abstract Percutaneous Coronary Intervention (PCI) is a widely utilized standard ofcare and efficacious intervention in the management of coronary artery disease,improving prognosis and symptoms for many patients. Prediction of post-PCIoutcomes contributes to effective patient management and quality improvementinitiatives in healthcare. Our study focuses on comparative performance analysisfor state-of-the-art vision transformer (ViT) and convolutional neural network(CNN) on multimodal data analysis in a joint fusion framework. We integrateimages of electrocardiogram (ECG) data and tabular electronic health records(EHR) to predict 3 clinically relevant post-PCI (6 months) endpoints - heart failure hospitalization, all-cause mortality, and ischemic stroke. To design a comparativemodel for ViT, we proposed a new joint fusion architecture that consistsof a convolutional neural network (CNN) with a convolutional block attentionmodule (CBAM). The learned representations are combined at an intermediatelayer followed by processing these representations using a fully connectedlayer. The proposed model demonstrates excellent performance with the highestAUROC scores of 0.849, 0.913, and 0.794 for predicting heart failure hospitalization,all-cause mortality, and stroke, respectively. Surpassing the baseline EHRmodel and ViT, the proposed CNN+CBAM fusion model showcases superiorpredictive capabilities for heart failure prediction.

This study aimed to analyze early revisits (within 48 hours of discharge) in an Emergency Department. Among the 178,295 visits, 11,686 were revisits, resulting in a rate of 6.55% (95%CI 6.43-6.67). A total of 1,410 revisits required hospitalization, and 252 were due to preventable errors (17.87%). These errors were mainly related to an inadequate therapeutic plan at discharge (47.22%), an incomplete diagnostic process (29.37%), and misdiagnoses (13.10%). These findings represent a technology-enabled clinical audit tool. Electronic Healthcare Records have the potential to: provide quality metrics of hospital performance, help to keep revisit rates updated (assessment through a real-time dashboard), and improve clinical management (by transparency initiatives about errors, and a supportive learning environment regarding lessons learned).

Current management of patients with congenital heart disease has increased their survival into adulthood. This is accompanied by potential cardiac complications, including pulmonary hypertension associated with congenital heart disease (PAH-CHD). PAH-CHD constitutes a challenging subgroup of pulmonary hypertension and requires expert management to improve quality of life and prognosis. Novel agents have shown a significant improvement in morbidity and mortality in patients with pulmonary arterial hypertension. However, the long-term effects of these medications on PAH-CHD patients remain somewhat uncertain, necessitating treatment plans largely founded on the clinical experience of the healthcare providers. The aim of this review is to summarize the current evidence and future perspectives regarding treatment strategies for PAH-CHD to help better guide management of this complex disease.

Introduction: Cardiac amyloidosis (CA) has been suggested to be common (up to 16%) in patients with severe aortic stenosis (AS) undergoing transcatheter aortic valve replacement (TAVR). CA has poorer outcomes and its assessment in all TAVR patients may be costly and challenging. Hypothesis: CA may be screened for with an artificial intelligence (AI) clinical predictive model applied to pre-TAVR ECGs, and high probability (>50%) for CA may be associated with worse clinical outcomes. Methods: In this retrospective analysis of the Mayo institutional National Cardiovascular Disease Registry (NCDR)-TAVR, patients undergoing a TAVR between Jan-2012 and Dec-2017 were included. Pre-TAVR ECGs were analyzed by the AI predictive model for CA embedded in the EMR. EMRs were reviewed to assess for a clinical diagnosis of CA in those identified as high probability (>50%) by the AI tool. Clinical outcomes on 1 year follow-up were extracted from the NCDR-TAVR database and Kaplan-Meier curves were created to compare patients with high CA probability (≥50%) versus those with low probability (<50%). Results: Of 1070 patients who underwent TAVR (mean age 81.1± 8.5 years, 58.2% male), 263 (24.6%) had ≥50% probability for CA on pre-procedure ECG. Only 18 (1.7%) of these had clinical diagnosis of CA. In the survival analysis, high probability of CA by AI tool was associated with higher all-cause mortality (HR 1.60, 95%CI 1.09-2.34, p=0.01) and greater HF admissions (HR 1.59, 95%CI 1.08-2.35, p<0.01). Neither TIA/stroke nor myocardial infarction were statistically significant. MACE (TIA/stroke, myocardial infarction, heart failure admissions) was higher in the ≥50% CA probability group (HR 1.68, 95%CI 1.17-2.40, p<0.01), (Figure) . Conclusion: CA is clinically underdiagnosed in patients undergoing TAVR. AI applied to pre-TAVR ECGs suggesting higher probability for CA identifies a subgroup at higher risk of clinical events, who may benefit from further diagnostic evaluation for CA.

Background: There is limited evidence regarding the impact of cardiac arrhythmias in patients with pulmonary arterial hypertension (PAH). We aim to comprehensively investigate the epidemiology and clinical outcomes of cardiac arrhythmias in patients with PAH. Methods: In a retrospective cohort study including 512 PAH patients from 2001-2021 at 3 Mayo Clinic sites, PAH patients were identified via echocardiogram, pulmonary function tests, and right heart catheterization. Demographic data at PAH diagnosis and clinical outcomes over a 10-year period were collected. The PAH patients were categorized into three groups based on arrhythmic onset: 1) patients with arrhythmia prior to PAH diagnosis, 2) patients diagnosed with arrhythmia during 10-year PAH follow-up, and 3) patients without arrhythmia during 10-year PAH follow-up. Survival outcomes were analyzed using multivariable Cox proportional hazards regression, adjusted with the REVEAL 2.0 score. Results: Among 512 PAH patients (mean age 56.1 years, 81.8% female), the prevalence of cardiac arrhythmias at PAH diagnosis was 10.5%. The cumulative incidences of new-onset arrhythmias at 1, 5, and 10 years were 6.6%, 18.4%, and 29.2%, respectively. Patients with arrhythmia diagnosed before and after PAH diagnosis showed significantly higher all-cause mortality rates with adjusted HR of 2.06 [95% CI 1.36-3.12] and 1.57 [95% CI 1.17-2.20] respectively (Figure 1). Similarly in both arrhythmic groups, there was a shorter median time to the first all-cause hospitalization (9.5 and 15.9 months vs. 21.2 months) and a higher number of all-cause hospitalizations (0.38 and 0.64 times per year vs. 0.10 times per year) compared to the non-arrhythmic group. Conclusions: Cardiac arrhythmias can develop in nearly one-third of PAH patients within 10 years of PAH diagnosis and independently contribute to increased mortality and hospitalization frequency.

Introduction: Exposure to high altitude results in hypobaric hypoxia, leading to physiological changes in the cardiovascular system that may result in dyspnea. Hypoxic simulation testing (HSTs) simulates changes in physiology that occur at a specific altitude. Hypothesis: The use of transthoracic echocardiography (TTE) during HST can detect the raise in right-sided pressures revealing underlying causes of high-altitude dyspnea. Methods: We performed a prospective observational study of consecutive patients with unexplained dyspnea at high altitude who were referred to an aerospace medicine program at a single institution between August 2021 and March 2023. Reduced FiO 2 was administered for 20 minutes to simulate altitude levels specific to patients’ history. TTE images were obtained at baseline and during peak hypoxia to evaluate right ventricular (RV) function, RV systolic pressure, and any possible shunts. Result: The study included 27 patients, with a mean age of 64.7 ±14.4 years and 14 (51.9%) females. No significant abnormalities were seen on baseline TTE and no significant differences in blood pressure and heart rate between baseline and hypoxia simulation were detected. Notably, RV systolic pressure increased at peak hypoxia, while RV systolic function declined as shown by a decrease in S’ wave and TAPSE ( Figure 1 ). Additionally, right to left shunts were present in 19 (70.4%) patients. Of these, four patients (21.1%) had shunts present at baseline with no changes at peak hypoxia, while the severity of shunts increased at peak hypoxia in eight cases (42.1%) and the shunts were only evident during hypoxia in seven patients (36.8%). Conclusion: TTE during HST provides valuable information by revealing the presence of symptomatic, sustained shunts and confirming the decline in RV hemodynamics explaining dyspnea at altitude. Further studies are necessary to establish the optimal clinical role of this physiologic method.

Introduction: The consequences of external cardiovascular compression and cardiac displacement from pectus excavatum (PEx) are debated. The complex geometry of the right (RV) and left ventricle (LV) along with distortion from the extrinsic chest deformity pose significant limitations to reliable assessment of LV and RV volumes and function using transthoracic 2D-echocardiography in this population. Hypothesis: A 3D-echocardiography approach can reliably assess the effects of external cardiac compression and the benefits of surgical correction on RV and LV function in PEx patients. Methods: Adult patients undergoing minimally invasive repair of PEx between Oct-2021 and Feb-2023 were included in this prospective study. Intraoperative transesophageal (TEE) 6 beat full volume video loops incorporating LV and RV were captured and compared before and after surgical correction of the PEx. TomTec Software® was used for offline 3D/4D reconstruction ( Figure 1 shows changes in 3D RV and LV shape pre- and post-surgery). Result: The study included 102 patients (mean age of 32.1 ±11.8 years; Haller index 4.9 ±2.5; 60.8% males). Post PEx repair, there was a significant (p<0.001) increase in the 3D RV volumes, RV ejection fraction (EF), RV stroke volume and RV strain ( Figure 1 ). Additionally, there was a significant improvement in 3D LVEF, 3D LV strain (longitudinal and circumferential), LV twist, and torsion ( Figure 1 ). Conclusion: In this PEx cohort, 3D/4D TEE imaging demonstrated significant increases in RV volumes and in RV and LV systolic function after surgical repair. These findings support the negative cardiovascular consequences of PEx compression and benefits of surgical repair.

Aortic valve stenosis (AS) is increasing in prevalence due to the aging population, and severe AS is associated with significant morbidity and mortality. Echocardiography remains the mainstay for the initial detection and diagnosis of AS, as well as for grading of severity. However, there are important subgroups of patients, for example, patients with low-flow low-gradient or paradoxical low-gradient AS, where quantification of severity of AS is challenging by echocardiography and underestimation of severity may delay appropriate management and impart a worse prognosis. Aortic valve calcium score by computed tomography has emerged as a useful clinical diagnostic test that is complimentary to echocardiography, particularly in cases where there may be conflicting data or clinical uncertainty about the degree of AS. In these situations, aortic valve calcium scoring may help re-stratify grading of severity and, therefore, further direct clinical management. This review presents the evolution of aortic valve calcium score by computed tomography, its diagnostic and prognostic value, as well as its utility in clinical care.

Chest radiography (CXR) is the most frequently performed radiological test worldwide because of its wide availability, non-invasive nature, and low cost. The ability of CXR to diagnose cardiovascular diseases, give insight into cardiac function, and predict cardiovascular events is often underutilized, not clearly understood, and affected by inter- and intra-observer variability. Therefore, more sophisticated tests are generally needed to assess cardiovascular diseases. Considering the sustained increase in the incidence of cardiovascular diseases, it is critical to find accessible, fast, and reproducible tests to help diagnose these frequent conditions. The expanded focus on the application of artificial intelligence (AI) with respect to diagnostic cardiovascular imaging has also been applied to CXR, with several publications suggesting that AI models can be trained to detect cardiovascular conditions by identifying features in the CXR. Multiple models have been developed to predict mortality, cardiovascular morphology and function, coronary artery disease, valvular heart diseases, aortic diseases, arrhythmias, pulmonary hypertension, and heart failure. The available evidence demonstrates that the use of AI-based tools applied to CXR for the diagnosis of cardiovascular conditions and prognostication has the potential to transform clinical care. AI-analyzed CXRs could be utilized in the future as a complimentary, easy-to-apply technology to improve diagnosis and risk stratification for cardiovascular diseases. Such advances will likely help better target more advanced investigations, which may reduce the burden of testing in some cases, as well as better identify higher-risk patients who would benefit from earlier, dedicated, and comprehensive cardiovascular evaluation.