A5043911290- Cardiac Imaging and Diagnostics
- COVID-19 Clinical Research Studies
- Cardiovascular Function and Risk Factors
- Amyloidosis: Diagnosis, Treatment, Outcomes
- Cardiac Valve Diseases and Treatments
- Artificial Intelligence in Healthcare and Education
- ECG Monitoring and Analysis
- Congenital Heart Disease Studies
- SARS-CoV-2 and COVID-19 Research
- Long-Term Effects of COVID-19
- Atrial Fibrillation Management and Outcomes
- Phonocardiography and Auscultation Techniques
- Cardiac, Anesthesia and Surgical Outcomes
- Cardiac electrophysiology and arrhythmias
- Radiation Dose and Imaging
- COVID-19 diagnosis using AI
- Machine Learning in Healthcare
- Advanced X-ray and CT Imaging
- Parathyroid Disorders and Treatments
- Artificial Intelligence in Healthcare
- Mechanical Circulatory Support Devices
- Emergency and Acute Care Studies
- Medical Imaging and Pathology Studies
- Non-Invasive Vital Sign Monitoring
- Lipoproteins and Cardiovascular Health
Columbia University
2019-2025
NewYork–Presbyterian Hospital
2020-2025
New York Hospital Queens
2020-2025
Columbia University Irving Medical Center
2017-2025
McGill University Health Centre
2023-2025
Montreal Children's Hospital
2023-2025
McGill University
2025
Presbyterian Hospital
2020-2024
New York Proton Center
2024
Stanford Health Care
2023
Abstract The coronavirus disease 2019 (COVID-19) can result in a hyperinflammatory state, leading to acute respiratory distress syndrome (ARDS), myocardial injury, and thrombotic complications, among other sequelae. Statins, which are known have anti-inflammatory antithrombotic properties, been studied the setting of viral infections, but their benefit has not assessed COVID-19. This is retrospective analysis patients admitted with COVID-19 from February 1 st through May 12 th , 2020 study...
Abstract Recent advances in large language models (LLMs) have demonstrated remarkable successes zero- and few-shot performance on various downstream tasks, paving the way for applications high-stakes domains. In this study, we systematically examine capabilities limitations of LLMs, specifically GPT-3.5 ChatGPT, performing zero-shot medical evidence summarization across six clinical We conduct both automatic human evaluations, covering several dimensions summary quality. Our study...
Valvular heart disease is an important contributor to cardiovascular morbidity and mortality remains underdiagnosed. Deep learning analysis of electrocardiography (ECG) may be useful in detecting aortic stenosis (AS), regurgitation (AR), mitral (MR). This study aimed develop ECG deep algorithms identify moderate or severe AS, AR, MR alone combination. A total 77,163 patients undergoing within 1 year before echocardiography from 2005-2021 were identified split into train (n = 43,165),...
Abstract The primary practice of healthcare artificial intelligence (AI) starts with model development, often using state-of-the-art AI, retrospectively evaluated metrics lifted from the AI literature like AUROC and DICE score. However, good performance on these may not translate to improved clinical outcomes. Instead, we argue for a better development pipeline constructed by working backward end goal positively impacting clinically relevant outcomes leading considerations causality in...
Preoperative risk assessments used in clinical practice are insufficient their ability to identify for postoperative mortality. Deep-learning analysis of electrocardiography can hidden markers that help prognosticate We aimed develop a prognostic model accurately predicts mortality patients undergoing medical procedures and who had received preoperative electrocardiographic diagnostic testing.
Recent advances in large language models (LLMs) have demonstrated remarkable successes zero- and few-shot performance on various downstream tasks, paving the way for applications high-stakes domains. In this study, we systematically examine capabilities limitations of LLMs, specifically GPT-3.5 ChatGPT, performing zero-shot medical evidence summarization across six clinical We conduct both automatic human evaluations, covering several dimensions summary quality. Our study has that metrics...
Abstract The electrocardiogram (ECG) is the most frequently performed cardiovascular diagnostic test, but it unclear how much information resting ECGs contain about long term risk. Here we report that a deep convolutional neural network can accurately predict long-term risk of mortality and disease based on ECG alone. Using large dataset 12-lead collected at Stanford University Medical Center, developed SEER, Estimator Electrocardiogram Risk. SEER predicts 5-year with an area under receiver...
Abstract Background and Aims Early identification of cardiac structural abnormalities indicative heart failure is crucial to improving patient outcomes. Chest X-rays (CXRs) are routinely conducted on a broad population patients, presenting an opportunity build scalable screening tools for Stage B or worse with deep learning methods. In this study, model was developed identify severe left ventricular hypertrophy (SLVH) dilated ventricle (DLV) using CXRs. Methods A total 71 589 unique CXRs...
BACKGROUND: Artificial intelligence, particularly deep learning (DL), has immense potential to improve the interpretation of transthoracic echocardiography (TTE). Mitral regurgitation (MR) is most common valvular heart disease and presents unique challenges for DL, including integration multiple video-level assessments into a final study-level classification. METHODS: A novel DL system was developed intake complete TTEs, identify color MR Doppler videos, determine severity on 4-step ordinal...
<h3>Importance</h3> Critical illness, a marked inflammatory response, and viruses such as SARS-CoV-2 may prolong corrected QT interval (QTc). <h3>Objective</h3> To evaluate baseline QTc on 12-lead electrocardiograms (ECGs) ensuing changes among patients with without COVID-19. <h3>Design, Setting, Participants</h3> This cohort study included 3050 aged 18 years older who underwent testing had ECGs at Columbia University Irving Medical Center from March 1 through May 1, 2020. Patients were...
Background Cardiovascular involvement in coronavirus disease 2019 (COVID‐19) is common and leads to worsened mortality. Diagnostic cardiovascular studies may be helpful for resource appropriation identifying patients at increased risk death. Methods Results We analyzed 887 (aged 64±17 years) admitted with COVID‐19 from March 1 April 3, 2020 New York City 12 lead electrocardiography within 2 days of diagnosis. Demographics, comorbidities, laboratory testing, including high sensitivity cardiac...
Electrocardiographic characteristics in COVID-19-related mortality have not yet been reported, particularly racial/ethnic minorities.We reviewed demographics, laboratory and cardiac tests, medications, rhythm proximate to death or initiation of comfort care for patients hospitalized with a positive SARS-CoV-2 reverse-transcriptase polymerase chain reaction three New York City hospitals between March 1 April 3, 2020 who died. We described clinical compared factors contributing toward...
Background: Type 2 diabetes is one of the most common chronic disorders worldwide and an important cause cardiovascular disease. Studies investigating risk atrial ventricular arrhythmias in diabetic patients taking different oral medications are sparse. Methods: We used IBM MarketScan Medicare Supplemental Database to examine for on by propensity score matching. Results: found that metformin monotherapy had significantly reduced arrhythmias, including fibrillation, compared with DPP4...
The 12-lead electrocardiogram (ECG) remains a cornerstone of cardiac diagnostics, yet existing artificial intelligence (AI) solutions for automated interpretation often lack generalizability, remain closed-source, and are primarily trained using supervised learning, limiting their adaptability across diverse clinical settings. To address these challenges, we developed compared two open-source foundational ECG models: DeepECG-SSL, self-supervised learning model, DeepECG-SL, model. Both models...
Abstract Objective Coronavirus disease 2019 (COVID-19) patients are at risk for resource-intensive outcomes including mechanical ventilation (MV), renal replacement therapy (RRT), and readmission. Accurate outcome prognostication could facilitate hospital resource allocation. We develop validate predictive models each using retrospective electronic health record data COVID-19 treated between March 2 May 6, 2020. Materials Methods For outcome, we trained 3 classes of prediction clinical a...
<title>Abstract</title> Heart failure (HF), a major global health challenge, affects millions worldwide and poses substantial healthcare economic burdens. The left ventricular ejection fraction (LVEF) is critical dynamic parameter used to characterize HF guide treatment. In this study, we developed validated an artificial intelligence (AI) model capable of predicting abnormal LVEF directly from static, non-gated, non-contrast chest computed tomography (CT) scans, novel application for...