Deep Learning for Echo Analysis, Tracking, and Evaluation of Mitral Regurgitation (DELINEATE-MR).

BACKGROUND: Artificial intelligence, particularly deep learning (DL), has immense potential to improve the interpretation of transthoracic echocardiography (TTE). Mitral regurgitation (MR) is the most common valvular heart disease and presents unique challenges for DL, including the integration of multiple video-level assessments into a final study-level classification. METHODS: A novel DL system was developed to intake complete TTEs, identify color MR Doppler videos, and determine MR severity on a 4-step ordinal scale (none/trace, mild, moderate, and severe) using the reading cardiologist as a reference standard. This DL system was tested in internal and external test sets with performance assessed by agreement with the reading cardiologist, weighted κ, and area under the receiver-operating characteristic curve for binary classification of both moderate or greater and severe MR. In addition to the primary 4-step model, a 6-step MR assessment model was studied with the addition of the intermediate MR classes of mild-moderate and moderate-severe with performance assessed by both exact agreement and ±1 step agreement with the clinical MR interpretation. RESULTS: A total of 61 689 TTEs were split into train (n=43 811), validation (n=8891), and internal test (n=8987) sets with an additional external test set of 8208 TTEs. The model had high performance in MR classification in internal (exact accuracy, 82%; κ=0.84; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR) and external test sets (exact accuracy, 79%; κ=0.80; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR). Most (63% internal and 66% external) misclassification disagreements were between none/trace and mild MR. MR classification accuracy was slightly higher using multiple TTE views (accuracy, 82%) than with only apical 4-chamber views (accuracy, 80%). In subset analyses, the model was accurate in the classification of both primary and secondary MR with slightly lower performance in cases of eccentric MR. In the analysis of the 6-step classification system, the exact accuracy was 80% and 76% with a ±1 step agreement of 99% and 98% in the internal and external test set, respectively. CONCLUSIONS: This end-to-end DL system can intake entire echocardiogram studies to accurately classify MR severity and may be useful in helping clinicians refine MR assessments.

COVID-19 and Cardiovascular Disease.

Coronavirus disease 2019 (COVID-19) is a global pandemic affecting 185 countries and >3 000 000 patients worldwide as of April 28, 2020. COVID-19 is caused by severe acute respiratory syndrome coronavirus 2, which invades cells through the angiotensin-converting enzyme 2 receptor. Among patients with COVID-19, there is a high prevalence of cardiovascular disease, and >7% of patients experience myocardial injury from the infection (22% of critically ill patients). Although angiotensin-converting enzyme 2 serves as the portal for infection, the role of angiotensin-converting enzyme inhibitors or angiotensin receptor blockers requires further investigation. COVID-19 poses a challenge for heart transplantation, affecting donor selection, immunosuppression, and posttransplant management. There are a number of promising therapies under active investigation to treat and prevent COVID-19.

The cardiac intensive care unit and the cardiac intensivist during the COVID-19 surge in New York City.

Critical care cardiology has been impacted by the coronavirus disease-2019 (COVID-19) pandemic. COVID-19 causes severe acute respiratory distress syndrome, acute kidney injury, as well as several cardiovascular complications including myocarditis, venous thromboembolic disease, cardiogenic shock, and cardiac arrest. The cardiac intensive care unit is rapidly evolving as the need for critical care beds increases. Herein, we describe the changes to the cardiac intensive care unit and the evolving role of critical care cardiologists and other clinicians in the care of these complex patients affected by the COVID-19 pandemic. These include practical recommendations regarding structural and organizational changes to facilitate care of patients with COVID-19; staffing and personnel changes; and health and safety of personnel. We draw upon our own experiences at NewYork-Presbyterian Columbia University Irving Medical Center to offer insights into the unique challenges facing critical care clinicians and provide recommendations of how to address these challenges during this unprecedented time.

Artificial Intelligence in Cardiovascular Care-Part 2: Applications: JACC Review Topic of the Week.

Recent artificial intelligence (AI) advancements in cardiovascular care offer potential enhancements in effective diagnosis, treatment, and outcomes. More than 600 U.S. Food and Drug Administration-approved clinical AI algorithms now exist, with 10% focusing on cardiovascular applications, highlighting the growing opportunities for AI to augment care. This review discusses the latest advancements in the field of AI, with a particular focus on the utilization of multimodal inputs and the field of generative AI. Further discussions in this review involve an approach to understanding the larger context in which AI-augmented care may exist, and include a discussion of the need for rigorous evaluation, appropriate infrastructure for deployment, ethics and equity assessments, regulatory oversight, and viable business cases for deployment. Embracing this rapidly evolving technology while setting an appropriately high evaluation benchmark with careful and patient-centered implementation will be crucial for cardiology to leverage AI to enhance patient care and the provider experience.

Artificial Intelligence for Cardiovascular Care-Part 1: Advances: JACC Review Topic of the Week.

Recent artificial intelligence (AI) advancements in cardiovascular care offer potential enhancements in diagnosis, treatment, and outcomes. Innovations to date focus on automating measurements, enhancing image quality, and detecting diseases using novel methods. Applications span wearables, electrocardiograms, echocardiography, angiography, genetics, and more. AI models detect diseases from electrocardiograms at accuracy not previously achieved by technology or human experts, including reduced ejection fraction, valvular heart disease, and other cardiomyopathies. However, AI's unique characteristics necessitate rigorous validation by addressing training methods, real-world efficacy, equity concerns, and long-term reliability. Despite an exponentially growing number of studies in cardiovascular AI, trials showing improvement in outcomes remain lacking. A number are currently underway. Embracing this rapidly evolving technology while setting a high evaluation benchmark will be crucial for cardiology to leverage AI to enhance patient care and the provider experience.

Examining medication ordering errors using AHRQ network of patient safety databases.

BACKGROUND: Studies examining the effects of computerized order entry (CPOE) on medication ordering errors demonstrate that CPOE does not consistently prevent these errors as intended. We used the Agency for Healthcare Research and Quality (AHRQ) Network of Patient Safety Databases (NPSD) to investigate the frequency and degree of harm of reported events that occurred at the ordering stage, characterized by error type. MATERIALS AND METHODS: This was a retrospective observational study of safety events reported by healthcare systems in participating patient safety organizations from 6/2010 through 12/2020. All medication and other substance ordering errors reported to NPSD via common format v1.2 between 6/2010 through 12/2020 were analyzed. We aggregated and categorized the frequency of reported medication ordering errors by error type, degree of harm, and demographic characteristics. RESULTS: A total of 12 830 errors were reported during the study period. Incorrect dose accounted for 3812 errors (29.7%), followed by incorrect medication 2086 (16.3%), and incorrect duration 765 (6.0%). Of 5282 events that reached the patient and had a known level of severity, 12 resulted in death, 4 resulted in severe harm, 45 resulted in moderate harm, 341 resulted in mild harm, and 4880 resulted in no harm. CONCLUSION: Incorrect dose and incorrect drug orders were the most commonly reported and harmful types of medication ordering errors. Future studies should aim to develop and test interventions focused on CPOE to prevent medication ordering errors, prioritizing wrong-dose and wrong-drug errors.

Deep Learning Electrocardiographic Analysis for Detection of Left-Sided Valvular Heart Disease.

BACKGROUND: Valvular heart disease is an important contributor to cardiovascular morbidity and mortality and remains underdiagnosed. Deep learning analysis of electrocardiography (ECG) may be useful in detecting aortic stenosis (AS), aortic regurgitation (AR), and mitral regurgitation (MR). OBJECTIVES: This study aimed to develop ECG deep learning algorithms to identify moderate or severe AS, AR, and MR alone and in combination. METHODS: A total of 77,163 patients undergoing ECG within 1 year before echocardiography from 2005-2021 were identified and split into train (n = 43,165), validation (n = 12,950), and test sets (n = 21,048; 7.8% with any of AS, AR, or MR). Model performance was assessed using area under the receiver-operating characteristic (AU-ROC) and precision-recall curves. Outside validation was conducted on an independent data set. Test accuracy was modeled using different disease prevalence levels to simulate screening efficacy using the deep learning model. RESULTS: The deep learning algorithm model accuracy was as follows: AS (AU-ROC: 0.88), AR (AU-ROC: 0.77), MR (AU-ROC: 0.83), and any of AS, AR, or MR (AU-ROC: 0.84; sensitivity 78%, specificity 73%) with similar accuracy in external validation. In screening program modeling, test characteristics were dependent on underlying prevalence and selected sensitivity levels. At a prevalence of 7.8%, the positive and negative predictive values were 20% and 97.6%, respectively. CONCLUSIONS: Deep learning analysis of the ECG can accurately detect AS, AR, and MR in this multicenter cohort and may serve as the basis for the development of a valvular heart disease screening program.

A Comprehensive Approach to Palliative Care during the Coronavirus Pandemic.

Context: The COVID-19 pandemic resulted in a surge of critically ill patients that strained health care systems throughout New York City in March and April of 2020. At the peak of the crisis, consults for palliative care increased four- to sevenfold at NewYork-Presbyterian (NYP), an academic health care system with 10 campuses throughout New York City. We share our challenges, solutions, and lessons learned to help peer institutions meet increased palliative care demands during future crises and address pre-existing palliative care subspecialist shortages during nonpandemic times. Methods: In response to the increased demand, palliative care physician and administrative leadership at NYP piloted multiple creative care models to expand access to palliative care outpatient and inpatient services. The care models included virtual outpatient management of existing patients, embedded palliative care staff, education for providers, multidisciplinary family support, hospice units (which allowed for family visitation), and team expansion through training other disciplines (primarily psychiatry) and deploying an ePalliative Care service (staffed by out-of-state volunteers). Conclusion: Our comprehensive response successfully expanded the palliative care team's reach, and, at the height of the pandemic, allowed our teams to meet the increased demand for palliative care consults. We learned that flexibility and adaptability were critical to responding to a rapidly evolving crisis. Physician and family feedback and preliminary data suggest that virtual outpatient visits, embedded staff, hospice units, and team expansion through training other disciplines and deploying ePalliative Care services were impactful interventions.

Transition of a Large Tertiary Heart Failure Program in Response to the COVID-19 Pandemic: Changes That Will Endure.

The coronavirus disease 2019 (COVID-19) pandemic imposed severe restrictions on traditional methods of patient care. During the pandemic, the heart failure program at New York-Presbyterian Hospital in New York, NY rapidly and comprehensively transitioned its care delivery model and administrative organization to conform to a new healthcare environment while still providing high-quality care to a large cohort of patients with heart failure, heart transplantation, and left ventricular assist device. In addition to the widespread adoption of telehealth, our program restructured outpatient care, initiating a shared clinic model and introducing a comprehensive remote monitoring program to manage patients with heart failure and heart transplant. All conferences, including administrative meetings, support groups, and educational seminars were converted to teleconferencing platforms. Following the peak of COVID-19, many of the new changes have been maintained, and the program structure will be permanently altered as a lasting effect of this pandemic. In this article, we review the details of our program's transition in the face of COVID-19 and highlight the programmatic changes that will endure.

Approach to Acute Cardiovascular Complications in COVID-19 Infection.

The novel coronavirus disease 2019, otherwise known as COVID-19, is a global pandemic with primary respiratory manifestations in those who are symptomatic. It has spread to >187 countries with a rapidly growing number of affected patients. Underlying cardiovascular disease is associated with more severe manifestations of COVID-19 and higher rates of mortality. COVID-19 can have both primary (arrhythmias, myocardial infarction, and myocarditis) and secondary (myocardial injury/biomarker elevation and heart failure) cardiac involvement. In severe cases, profound circulatory failure can result. This review discusses the presentation and management of patients with severe cardiac complications of COVID-19 disease, with an emphasis on a Heart-Lung team approach in patient management. Furthermore, it focuses on the use of and indications for acute mechanical circulatory support in cardiogenic and/or mixed shock.

Restructuring Electrophysiology During the COVID-19 Pandemic: A Practical Guide From a New York City Hospital Network.

The coronavirus disease 2019 crisis is a global pandemic of a novel infectious disease with far-ranging public health implications. With regard to cardiac electrophysiology (EP) services, we discuss the "real-world" challenges and solutions that have been essential for efficient and successful (1) ramping down of standard clinical practice patterns and (2) pivoting of workflow processes to meet the demands of this pandemic. The aims of these recommendations are to outline: (1) essential practical steps to approaching procedures, as well as outpatient and inpatient care of EP patients, with relevant examples, (2) successful strategies to minimize exposure risk to patients and clinical staff while also balancing resource utilization, (3) challenges related to redeployment and restructuring of clinical and support staff, and (4) considerations regarding continued collaboration with clinical and administrative colleagues to implement these changes. While process changes will vary across practices and hospital systems, we believe that these experiences from 4 different EP sections in a large New York City hospital network currently based in the global epicenter of the coronavirus disease 2019 pandemic will prove useful for other EP practices adapting their own practices in preparation for local surges.

The Prognostic Value of Electrocardiogram at Presentation to Emergency Department in Patients With COVID-19.

OBJECTIVE: To study whether combining vital signs and electrocardiogram (ECG) analysis can improve early prognostication. METHODS: This study analyzed 1258 adults with coronavirus disease 2019 who were seen at three hospitals in New York in March and April 2020. Electrocardiograms at presentation to the emergency department were systematically read by electrophysiologists. The primary outcome was a composite of mechanical ventilation or death 48 hours from diagnosis. The prognostic value of ECG abnormalities was assessed in a model adjusted for demographics, comorbidities, and vital signs. RESULTS: At 48 hours, 73 of 1258 patients (5.8%) had died and 174 of 1258 (13.8%) were alive but receiving mechanical ventilation with 277 of 1258 (22.0%) patients dying by 30 days. Early development of respiratory failure was common, with 53% of all intubations occurring within 48 hours of presentation. In a multivariable logistic regression, atrial fibrillation/flutter (odds ratio [OR], 2.5; 95% CI, 1.1 to 6.2), right ventricular strain (OR, 2.7; 95% CI, 1.3 to 6.1), and ST segment abnormalities (OR, 2.4; 95% CI, 1.5 to 3.8) were associated with death or mechanical ventilation at 48 hours. In 108 patients without these ECG abnormalities and with normal respiratory vitals (rate <20 breaths/min and saturation >95%), only 5 (4.6%) died or required mechanical ventilation by 48 hours versus 68 of 216 patients (31.5%) having both ECG and respiratory vital sign abnormalities. CONCLUSION: The combination of abnormal respiratory vital signs and ECG findings of atrial fibrillation/flutter, right ventricular strain, or ST segment abnormalities accurately prognosticates early deterioration in patients with coronavirus disease 2019 and may assist with patient triage.