Kashou, Anthony H.

Introduction: Infective endocarditis (IE) is a severe intracardiac infection, often requiring intensive care unit (ICU) admission. Despite early surgical intervention, mortality remains high. Data for patients admitted to the cardiac intensive care unit (CICU) is especially limited. Research Question: We aimed to investigate the short and long-term outcomes of patients with IE admitted to the CICU. Methods: We conducted a retrospective cohort study of adult patients admitted to the Mayo Clinic CICU (2007-2018) with confirmed acute IE, identified via database query and manual chart review. Patients were further categorized by cardiac surgery status: performed, indicated but declined, or not indicated. Primary outcomes were all-cause mortality at 30-days and 1-year, analyzed using Kaplan-Meier and Cox proportional-hazard analysis. Models were adjusted for known predictors. Results: Overall, 233 CICU patients met criteria for IE. Median age was 64.0 years; 49 were female. In total, 104 patients had native valve IE; 128 had prosthetic or implantable device-associated IE. Staphylococcus aureus was the most prevalent organism (42.7%) and was present in 72.4% of 30-day deaths. Cardiac surgery was indicated in 182 (78.1%) patients - 129 patients underwent surgery, while 53 declined; 48 patients did not have indications. By 30 days, 58 (24.9%) patients died; significant predictors included older age, higher illness severity scores, and greater need for critical care therapies. The 30-day mortality estimates were markedly higher for patients who declined surgery (60.4%, adj. HR 4.17, 95% CI 2.02-8.52, p <0.001), and lower for those who received surgery vs those without surgical indications (11.9% vs 23.8%, adj. HR 0.44, 95% CI 0.20-0.98, p=0.04) (Figure 1). By 1-year, 93 (39.9%) patients died, including 36 (20.5%) hospital survivors. The 1-year mortality estimates were markedly higher for patients who declined surgery (85.1%, adj. HR 5.46, 95% CI 2.87-10.39, p <0.001), but was similar for patients who received surgery to those without surgical indications (31.8% vs 29.3%, adj. HR 0.94, 95% CI 0.49-1.78, p=0.84) (Figure 2). Conclusion: IE requiring CICU admission carries substantial mortality despite acute management. Higher severity scores, comorbidities, and intensive care interventions predict mortality. Early cardiac surgery improved short-term outcomes, but long-term mortality remains high.

Abstract Advancements in machine learning and computing methods have given new life and great excitement to one of the most essential diagnostic tools to date—the electrocardiogram (ECG). The application of artificial intelligence‐enabled ECG (AI‐ECG) has resulted in the ability to identify electrocardiographic signatures of conventional and unique variables and pathologies, giving way to tremendous clinical potential. However, what these AI‐ECG models are detecting that the human eye is missing remains unclear. In this article, we highlight some of the recent developments in the field and their potential clinical implications, while also attempting to shed light on the physiologic and pathophysiologic features that enable these models to have such high diagnostic yield. © 2022 American Physiological Society. Compr Physiol 12:3417‐3424, 2022.

Abstract Background Atrial high-rate episodes (AHRE) are commonly detected in individuals with cardiac implantable electronic devices. Outcomes of atrial high-rate episodes remain unclear in those without a prior history of atrial fibrillation. Purpose This study aims to evaluate clinical outcomes of atrial high-rate episodes in patients who have no prior history of atrial fibrillation. Methods PubMed, EMBASE, and Cochrane databases were searched through February 2024 for studies evaluating clinical outcomes in individuals with cardiac implantable electronic devices who experienced atrial high-rate episodes, compared to those who did not. Individuals who had a prior history of atrial fibrillation were excluded. Outcomes assessed were clinical atrial fibrillation, thromboembolic events, and all-cause mortality. A fixed-effects model was used to calculate risk ratios (RRs) with 95% confidence intervals (CI). A subgroup analysis of thromboembolic events was conducted based on the duration of atrial high-rate episodes. Results A total of 9 studies met inclusion criteria with a combined enrollment of 7440 patients. Compared to those who did not experience atrial high-rate episodes, those who did had significantly increased risks of clinical atrial fibrillation (RR 3.33; 95% CI 1.99 - 5.57; P &lt; 0.0001) and thromboembolic events (RR 2.21; 95% CI 1.72 -2.85; P &lt; 0.0001). The risk of all-cause mortality was similar between both groups (RR 1.19; 95% CI 0.95 – 1.49; P = 0.13). Subgroup analysis revealed an increased risk of thromboembolic events among atrial high-rate episodes ≥ 24 hours (RR 12.34; 95% CI 2.70 – 56.36) while atrial high-rate episodes lasting &lt; 24 hours were insignificantly associated with thromboembolic events (RR 0.83; 95% CI 0.12 – 5.58). Conclusions Our study indicates a heightened risk of clinical atrial fibrillation and thromboembolic events among patients with atrial high-rate episodes, with no observed increase in mortality risk. Furthermore, our findings suggest that the duration of atrial high-rate episodes influences the risk of thromboembolism. Further studies are warranted to confirm our findings.

BACKGROUND: Differentiating wide complex tachycardias (WCTs) into ventricular tachycardia (VT) and supraventricular wide tachycardia via 12-lead ECG interpretation is a crucial but difficult task. Automated algorithms show promise as alternatives to manual ECG interpretation, but direct comparison of their diagnostic performance has not been undertaken. METHODS: Two electrophysiologists applied 3 manual WCT differentiation approaches (ie, Brugada, Vereckei aVR, and VT score). Simultaneously, computerized data from paired WCT and baseline ECGs were processed by 5 automated WCT differentiation algorithms (WCT Formula, WCT Formula II, VT Prediction Model, Solo Model, and Paired Model). The diagnostic performance of automated algorithms was compared with manual ECG interpretation approaches. RESULTS: A total of 212 WCTs (111 VT and 101 supraventricular wide tachycardia) from 104 patients were analyzed. WCT Formula demonstrated superior accuracy (85.8%) and specificity (87.1%) compared with Brugada (75.2% and 57.4%, respectively) and Vereckei aVR (65.3% and 36.4%, respectively). WCT Formula II achieved higher accuracy (89.6%) and specificity (85.1%) against Brugada and Vereckei aVR. Performance metrics of the WCT Formula (accuracy 85.8%, sensitivity 84.7%, and specificity 87.1%) and WCT Formula II (accuracy 89.8%, sensitivity 89.6%, and specificity 85.1%) were similar to the VT score (accuracy 84.4%, sensitivity 93.8%, and specificity 74.2%). Paired Model was superior to Brugada in accuracy (89.6% versus 75.2%), specificity (97.0% versus 57.4%), and F1 score (0.89 versus 0.80). Paired Model surpassed Vereckei aVR in accuracy (89.6% versus 65.3%), specificity (97.0% versus 75.2%), and F1 score (0.89 versus 0.74). Paired Model demonstrated similar accuracy (89.6% versus 84.4%), inferior sensitivity (79.3% versus 93.8%), but superior specificity (97.0% versus 74.2%) to the VT score. Solo Model and VT Prediction Model accuracy (82.5% and 77.4%, respectively) was superior to the Vereckei aVR (65.3%) but similar to Brugada (75.2%) and the VT score (84.4%). CONCLUSIONS: Automated WCT differentiation algorithms demonstrated favorable diagnostic performance compared with traditional manual ECG interpretation approaches.

Background: Outcomes of device-detected AF remain unclear in individuals without a prior history of AF. Methods: A meta-analysis was conducted to evaluate outcomes in individuals with no prior history of AF who experienced device-detected AF. Outcomes assessed were clinical AF, thromboembolism and all-cause mortality. A fixed-effects model was used to calculate RRs with 95% CI. Results: Compared to individuals who did not experience device-detected AF, those who did had increased risks of clinical AF (RR 3.33, 95% CI [1.99–5.57]; p<0.0001) and thromboembolic events (RR 2.21; 95% CI [1.72–2.85]; p<0.0001). The risk of all-cause mortality was similar between both groups (RR 1.19; 95% CI [0.95–1.49]; p=0.13). Subgroup analysis revealed an increased risk of thromboembolic events among device-detected AF ≥24 hours (RR 12.34; 95% CI [2.70–56.36]). Conclusion: While there is an increased risk of clinical AF and thromboembolism in individuals with device-detected AF, mortality was insignificant.

Background: Atrial septal defects (ASD) and ventricular septal defects (VSD) are among the most common forms of congenital heart disease (CHD). Early detection and intervention for these defects are crucial to prevent complications. Given advancements in AI technology, the development of AI-enabled ECG models for detecting these defects is of significant interest. Aims: This study aimed to create AI models using pediatric ECG data for the detection of ASD, VSD, and a combined model detecting either ASD or VSD. Methods: We analyzed a dataset of 7,795 pediatric patients from Mayo Clinic who had undergone echocardiography between 2002 and 2022, with corresponding 10-second, 12-lead surface ECGs taken within 14 days of echocardiography. This dataset included 259 patients with ASDs and 139 patients with VSDs (single or multiple). The control group was comprised of 7,397 patients without significant or complex CHD. For cases and controls, we included patients with all forms of electrocardiographic abnormalities and those with valvular lesions who had less than moderate stenosis or regurgitation. The dataset was divided into training, validation, and testing subsets to develop convolutional neural network (CNN) models for ASD, VSD, and either ASD or VSD detection. Results: Our ASD and VSD detection models achieved test AUCs of 0.82 (95% CI 0.76, 0.88) and 0.80 (95% CI 0.70, 0.90), respectively. Meanwhile, a combined model that detected either ASD or VSD demonstrated a test AUC of 0.81 (95% CI, 0.76, 0.86), sensitivity of 0.73, specificity of 0.76, PPV of 0.14, and NPV of 0.98 (Figure 1). Conclusions: AI-enabled ECG models demonstrate promising performance in detecting ASD and VSD in pediatric patients. A combined model that detects either ASD or VSD also shows robust results. Future research should focus on multi-center validation of these models, refining their diagnostic capacities, and investigating their potential for early intervention in CHDs.

Introduction: Left and right ventricular systolic dysfunction (LVSD and RVSD respectively) contribute to considerable pediatric morbidity. Both LVSD and RVSD can occur in children before symptom onset, emphasizing the need for early detection. Existing deep-learning algorithms can identify LVSD in adults using 12-lead ECG; however, their efficacy in children is uncertain. Aims: We aimed to create a deep-learning model for LVSD and RVSD detection in pediatric patients using an AI-enabled ECG and compare novel pediatric models to a previously validated adult LVSD model. Methods: We identified 10,214 pediatric patients at the Mayo Clinic with a transthoracic echocardiogram (TTE) and a 10-second, 12-lead surface ECG within 14 days of TTE, performed from 2002 -2022. Our cohort comprised the first TTE-ECG pair from each patient, totaling 138 with EF ≤ 35%, 312 with EF ≤ 50%, 482 with RVSD, and 9,567 without any LVSD or RVSD. The cohort was split into training, validation, and testing datasets to develop neural networks for systolic dysfunction detection. Results: The cohort was 52.3% male, with an average age of 10.3 years. Novel models generated in the pediatric cohort demonstrated excellent performance in systolic dysfunction detection (Figure 1). Pediatric models for EF ≤ 35% and EF ≤ 50% achieved test AUCs of 0.92 (95% CI 0.89, 0.95) and 0.89 (95% CI 0.85, 0.94) respectively. The RVSD model reached a test AUC of 0.91 (95% CI 0.88, 0.94). A combined model for EF ≤ 35% or RVSD exhibited a test AUC of 0.90 (95% CI 0.87, 0.93), sensitivity 0.88, specificity 0.82, PPV 0.20, and NPV 0.95. A combined model for EF ≤ 50% or RVSD exhibited a test AUC of 0.88 (95% CI 0.85, 0.91). The previously validated adult data-derived model achieved an AUC of 0.86 (95% CI 0.83, 0.89) for EF ≤ 50% in children. Conclusions: AI-enabled ECGs demonstrate efficient detection of both LVSD and RVSD in pediatric patients. Future multi-site validation is needed to further establish the reliability of these models.

Introduction: Biologic sex and hormonal concentrations shape ECG parameters due to sex hormone effects on cardiac function. AI-enabled ECGs have previously been shown to accurately predict patient sex in adults and correlate with sex hormone levels. Aims: We aimed to test the ability of AI-enabled ECGs to predict pediatric patient sex and explore the influence of pubertal development. Methods: Two AI-enabled ECG models were created using a convolutional neural network trained on pediatric 10-second, 12-lead surface ECGs. The first model was trained de novo using pediatric data. The second model used transfer learning from a previously validated adult data-derived algorithm. We analyzed the first ECG from 89,063 pediatric patients (aged <19 years) recorded from 1988-2022, and divided the cohort into training, validation, and testing datasets. Subgroup analysis was performed on prepubertal (0-7 years), pubertal (8-14 years), and post-pubertal (15-18 years) patients. Results: The cohort consisted of 46.6% males, with 21,434 prepubertal, 26,300 pubertal, and 41,329 post-pubertal children. No significant performance difference was observed between the two models. Both models demonstrated 81% accuracy and an overall AUC of 0.91 in the testing cohorts, with high discriminatory ability in post-pubertal teenagers (AUC = 0.98). (Figure 1) Conclusions: AI-ECG predicts pediatric patient sex with varying performance across pubertal stages. The highest discriminatory ability is observed post-puberty, decreasing in pubertal and prepubertal children. The results suggest hormonal and physiological changes during puberty may influence cardiac electrophysiology measurably. More research is required to interpret CNN-predicted sex discordance with actual sex and its implications for future cardiovascular risk.