Citations

Abstract Accurate molecular diagnostic tests are necessary for confirming a diagnosis of coronavirus disease 2019 (COVID-19) and for identifying asymptomatic carriage of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The number of available SARS-CoV-2 nucleic acid detection tests continues to increase as does the COVID-19 diagnostic literature. Thus, the Infectious Diseases Society of America (IDSA) developed an evidence-based diagnostic guideline to assist clinicians, clinical laboratorians, patients, and policymakers in decisions related to the optimal use of SARS-CoV-2 nucleic acid amplification tests. In addition, we provide a conceptual framework for understanding molecular diagnostic test performance, discuss nuances of test result interpretation in a variety of practice settings, and highlight important unmet research needs related to COVID-19 diagnostic testing. IDSA convened a multidisciplinary panel of infectious diseases clinicians, clinical microbiologists, and experts in systematic literature review to identify and prioritize clinical questions and outcomes related to the use of SARS-CoV-2 molecular diagnostics. Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology was used to assess the certainty of evidence and make testing recommendations. The panel agreed on 12 diagnostic recommendations. Access to accurate SARS-CoV-2 nucleic acid testing is critical for patient care, hospital infection prevention, and the public health response to COVID-19 infection. Information on the clinical performance of available tests continues to grow, but the quality of evidence of the current literature to support this updated molecular diagnostic guideline remains moderate to very low. Recognizing these limitations, the IDSA panel weighed available diagnostic evidence and recommends nucleic acid testing for all symptomatic individuals suspected of having COVID-19. In addition, testing is suggested for asymptomatic individuals with known or suspected contact with a COVID-19 case when the results will impact isolation/quarantine/personal protective equipment (PPE) usage decisions. Evidence in support of rapid testing and testing of upper respiratory specimens other than nasopharyngeal swabs, which offer logistical advantages, is sufficient to warrant conditional recommendations in favor of these approaches.

Introduction/Background: Cardiopulmonary arrest (Code Blue or CB) is a feared complication of severe medical illnesses. In-hospital CB events (CBE) have been estimated to have a mortality rate of only 30.4%. CBEsare difficult to prepare for and execute due many factors, including their low frequency, high complexity, and unpredictability. Research Questions/Hypothesis: Over 6 months (March - September 2019), we tested the effects of both adaptation of a Code Blue (CB) Team Leader (TL) checklist—aimed at improving resident leadership and communication—as well as implementation of an interdisciplinary in-hospital CB simulation to improve the performance of both resident physicians. Methods/Approach: Primary outcomes included change in resident confidence leading a CBE (i.e. Level of comfort as TL , confidence of diagnosis and management, confidence in code-related procedural skills), and familiarity with the institutional rapid response protocol. Secondary outcomes included self-reported confidence of nurses to execute their role, and both physician and nurse time to response. Confidence parameters were measured by a 10 point Likert scale. Pre-intervention, baseline cross-sectional survey values of the primary outcome were obtained from 24 internal medicine residents (12 PGY2s, 12 PGY3) over 6 months. Post-intervention, the cross-sectional survey was repeated. Results/Data (descriptive and inferential statistics): Statistics for residents displayed in table and figure 1. The level of nurse confidence increased from 7.5 to 8.25 over 5 months. The time to first response by residents has decreased by more than 50%. Conclusion(s) Our project improved the quality and resident level of comfort running Code Blue events among both residents and nurses.

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.

Background: Geographic and temporal distribution of disparity authorships is unclear. Our aim was to examine authorship trends in 2020-2023 American Heart Association (AHA) abstracts reporting social and demographic disparities. Methods: We reviewed 801 AHA conference abstracts, analyzing 723 reports. Regional information of authors and their reported disparities related to gender, race, region, healthcare access (HCA), comorbidities (CO), socioeconomic status (SES) were collected. Descriptive and trend analyses were performed using Chi-square tests, and Pearson's and Kendall's Tau b correlation tests. P <0.05 was considered significant. Results: We analyzed 1440 primary and senior authorships from 723 abstracts. The majority of authors (92%) were from North America, predominantly USA (90%), with a significant representation from the South (33.6%) vs. other regions (Image 1). Disparities on outcomes such as race, gender, SES, CO, geographical locations, and HCA were reported as 53.9%, 33.9%, 26.6%, 24.9%, 17.8%, and 13.6% respectively. From 2020 to 2023, there was a declining trend in authors reporting on gender (ptrend<0.001) and HCA (ptrend-0.03) disparities, whereas disparities on SES had an increasing trend (ptrend<0.001). An increase in reporting of gender disparities was associated with increased reporting of racial disparities (r = .081, τb = .081). We also found positive correlations between SES and HCA (r = .155, τb = .155). Conversely, there was a negative correlation between gender and SES (r = -0.133, τb = -0.133), and between CO and healthcare access HCA (r = -0.078, τb = -0.078). All correlations were statistically significant (p < 0.05). Conclusion: The trends show that authors have reported more SES disparities in recent times compared to HCA, race, and gender. With expected financially challenging times ahead, to address these findings, it remains important to focus research on income based equalities in HCA and outcomes.

Background: Ca-NBTE primarily affects the mitral valve (MV) and aortic valve (AV), with rare involvement of the right heart valves. Premortem descriptions of this condition are limited to a few case reports. This study presents an initial clinical series focusing on patients with Ca-NBTE specifically affecting their right heart valves. We describe the underlying cancers, types of valve lesions, and associated embolic complications. Patients and Methods: A electronic search of medical records (March 31, 2002, to June 30, 2022) was followed by a manual review to identify adult patients with echocardiographically detected NBTE, active cancer, and no infectious endocarditis or lupus anticoagulant/antiphospholipid antibodies. Results: Out of 115 identified patients with Ca-NBTE (mean age 63.2±9.7 years, 66.1% female), there were 8 cases (7.0%) affecting right heart valves (mean age 64.5±12.1 years, 3 females) with underlying cancer: pancreatic (n=3), lung (n= 2), genitourinary (n=1), gastric (n=1) and neck sarcomatoid carcinoma (n=1). TV was affected in 8 patients and PV in one case; 4 patients had Ca-NBTE limited only to PV, 2 patients had MV and TV, 1 patient had mitral, aortic and TV, and 1 patient with pancreatic cancer had all four valves affected by NBTE. 5 patients had embolic complications to the brain with one patient in that group also experiencing emboli to the kidney and spleen. Out of 4 patients with NBTE limited to TV, two still had brain emboli, one had only pulmonary embolism, and one patient had no embolic complications. Conclusion: Around 7% of Ca-NBTE cases involve the right heart valves, with half of these cases limited to the TV. The cancer profile in these cases resembles that seen in left heart valve involvement.

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.

Background: Our team has previously developed convolutional neural networks (CNNs) to estimate age and sex from a 10-second, 12-lead ECG as indicators of patient wellness. Here, we develop an additional wellness network to estimate body mass index (BMI) from the ECG input signal. Aims: To evaluate the performance of neural networks trained to classify and directly estimate BMI. Methods: We identified all adult patients in the Mayo Clinic system who had a 10-second, 12-lead ECG within 15 days of a BMI measurement. Of the&nbsp;174,863 patients in the cohort, 2,895 were underweight (BMI < 18.5), 42,387 were of normal weight (BMI 18.5-24.9), and 57,939 were overweight only (BMI 25.0-29.9). Among patients categorized as obese, 39,788 had class I obesity (BMI 30.0-34.9), 18,978 had class II obesity (BMI 35.0-39.9), and 12,876 had class III obesity (BMI ≥ 40.0). The cohort was split into training, validation, and testing datasets in an 8:1:1 ratio to develop networks for BMI classification and a direct&nbsp;estimation of BMI. Results: In detecting overweight in the testing set, the model achieved an AUC of 0.86 (95% CI 0.85, 0.87). In detecting class I, class II, and class III obesity, the model yielded AUCs of 0.84 (95% CI 0.83, 0.85), 0.84 (95% CI 0.83, 0.85), and 0.85 (95% CI 0.85, 0.86), respectively. The model to estimate BMI achieved a mean absolute error of 3.70. Conclusions: AI-enabled ECGs demonstrate efficient detection of overweight patients and all classes of obesity. Further research is needed to determine if discrepancies between the traditionally measured BMI and the AI-ECG BMI reflect the presence or lack of metabolic abnormalities.

Background: Enlargement or dilation of the left ventricle (LV) is associated with increased cardiovascular morbidity and mortality, and is an established precursor of ventricular dysfunction and heart failure in almost all major cardiovascular conditions. Although there are existing artificial intelligence frameworks that make use of deep learning to detect LV enlargement, many entail LV segmentation, which can be error-prone especially for point-of-care ultrasound (POCUS) images. Goal: To develop a fully end-to-end deep learning framework that takes as input either transthoracic echocardiographic (TTE) or POCUS 2D image clips, and classifies directly (i.e., without first segmenting the LV) whether a patient has an enlarged LV. Methods: Using a sample of retrospective TTE data enriched for LV enlargement (out of 13,868 patients total, 3,351 had an enlarged LV defined using sex-specific guideline-directed criteria), we trained a classifier that takes as input apical 2-chamber and parasternal long axis videos, and provides as output a binary label denoting whether a patient has an enlarged LV. Then, we evaluated the trained model using a holdout testing dataset of retrospective TTE data (2,087 patients) as well as data from a prospective cohort of 428 patients from whom TTE and POCUS were collected simultaneously. Results: For the retrospective TTE testing dataset, the AUC was 0.851 (95% confidence interval (CI) of 0.830-871). For the prospective cohort, the model performed comparably for both TTE and POCUS video clips (TTE: AUC of 0.865, 95% CI of 0.823-0.906; POCUS: AUC of 0.840, 95% CI of 0.797-0.883). Conclusions: The current deep learning model performed comparably well for both TTE and POCUS echocardiograms. We regard these results as a proof-of-concept of the potential utility of this model in helping point-of-care clinicians make decisions regarding whether patients should receive further evaluation for LV enlargement and associated conditions.

Introduction: Artificial intelligence applied to electrocardiograms (ECG-AI) enables early and efficient detection of cardiovascular disease. The technical and clinical impact of different approaches to designing ECG-AI remains under-explored. We consider left ventricular hypertrophy (LVH) and examine the impact of disease-specific labeling of minority etiologies of left ventricular wall thickening- hypertrophic cardiomyopathy (HCM) and cardiac amyloidosis (CA) - on ECG-AI performance. Hypothesis: ECG-AI designed to detect HCM or CA outperforms ECG-AI broadly trained to identify LVH due to differences in attention to key ECG features associated with HCM or CA. Methods: Independent neural networks were trained to identify HCM, CA, and LVH. HCM and CA patients were identified using the full depth of EHR data and validated via clinician adjudication (N = 3,025 and 4,251 patients, respectively). Moderate and severe LVH patients (N = 98,144) were identified using echocardiogram results and international LVH criteria. We compared the ability of disease-specific ECG-AI vs. LVH ECG-AI to detect HCM (or CA) by examining model performance within each of the three test sets. Results: 52.6% of HCM patients and 49.5% of CA patients met LVH criteria. Within the HCM test set, the AUROC, sensitivity, specificity, and positive predictive value (PPV) of the HCM ECG-AI were 0.94, 0.88, 0.85, and 60%, respectively, whereas the same for LVH ECG-AI were 0.83, 0.83, 0.64, and 37%. Within the CA test set, CA ECG-AI achieved AUROC, sensitivity, specificity, and PPV of 0.94, 0.81, 0.91, and 69%, respectively, whereas the same for LVH ECG-AI were 0.75, 0.73, 0.68, and 31%. ECGs positive for HCM exhibited higher P wave area, QRS deflection and R wave amplitude compared to LVH-positive ECGs (Cohen's D > 0.75). ECGs positive for CA exhibited lower R wave amplitude/area, QRS deflection and QRS areas (Cohen's D > 0.6). Conclusion: Models trained using carefully labeled HCM or CA identify distinct signals associated with the diseases, resulting in improved disease discrimination compared to a model trained to identify echocardiographic left ventricular thickening. Labeling choices should be communicated transparently to clinicians to ensure safe and effective use of ECG-AI.

Introduction: α-Klotho (klotho) is a geroprotective protein inversely associated with coronary artery disease CAD and vascular aging. This study used intravascular ultrasound (IVUS) to study coronary artery plaque characteristics of patients with low circulating klotho. Hypothesis: Lower klotho is associated with vulnerable coronary artery plaque characteristics. Methods: Patients undergoing coronary angiogram for chest pain who had no CAD (<40% stenosis) underwent IVUS assessment. Images were obtained from the mid-LAD to the coronary ostium. Stored arterial plasma was used for α-klotho analysis by enzyme-linked immunosorbent assay. Results: A total of 58 consecutive patients were retrospectively studied. The median circulating klotho level of the cohort was 0.27 ng/mL [0.15; 1.24]. Patients with klotho less than the median were compared to those with levels greater than or equal to the median and were similar in age (53 ±11 vs. 56 ±10, p = 0.235) and sex distribution (86% vs. 76% female, p = 0.324). Patients with less klotho had higher coronary plaque burden (21.42% [17.185, 31.955] vs. 18.32 [10.5, 24.515], p=0.041) and larger plaque area (2.71 [2.03, 4.605] vs . 2.27 [1.41, 3.31] mm 3 /mm, p=0.058) compared to those with higher klotho. Lower klotho was associated with vulnerable plaque characteristics, including greater percentages of dense calcium (1.33% [0.265, 5.38] vs. 0.43% [0.015, 1.73], p=0.037) and necrotic core (5.43% [2.245, 10.5] vs. 2.22% [0.86, 4.50], p=0.011). Conclusions: Lower circulating klotho was associated with higher coronary plaque burden and vulnerable plaque characteristics. Klotho may be an early biomarker for risk in coronary artery disease.