A5059615819- ECG Monitoring and Analysis
- Cardiac electrophysiology and arrhythmias
- Cardiac Imaging and Diagnostics
- Diabetes and associated disorders
- Pancreatic function and diabetes
- Atrial Fibrillation Management and Outcomes
- Phonocardiography and Auscultation Techniques
- Cardiac, Anesthesia and Surgical Outcomes
- Cardiac Arrhythmias and Treatments
- Cardiovascular Function and Risk Factors
- Diabetes Management and Research
- Enzyme Structure and Function
- Cardiovascular Health and Risk Factors
- Artificial Intelligence in Healthcare and Education
- T-cell and B-cell Immunology
- Acute Myocardial Infarction Research
- Cardiac pacing and defibrillation studies
- Immune Cell Function and Interaction
- Anesthesia and Pain Management
- Heart Rate Variability and Autonomic Control
- Enhanced Recovery After Surgery
- Pharmacological Effects and Toxicity Studies
- Magnesium in Health and Disease
- Neurological Complications and Syndromes
- Neurological and metabolic disorders
Stanford University
2018-2025
Cardiovascular Institute of the South
2024-2025
Stanford Medicine
2019-2023
University of California, San Francisco
2022-2023
Palo Alto University
2020
Yale University
2012-2016
Johns Hopkins University
2011
University of Arizona
2007-2010
St Michael's Hospital
2008
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.
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...
Humanized mice can be successfully used as a preclinical testing platform to identify the mechanism of action immunotherapies in humans.
The mechanisms whereby immune therapies affect progression of type 1 diabetes (T1D) are not well understood. Teplizumab, an FcR nonbinding anti‐CD3 mAb, has shown efficacy in multiple randomized clinical trials. We previously reported increase the frequency circulating CD8 + central memory (CD8CM) T cells responders, but generalizability this finding and molecular effects teplizumab on these have been evaluated. analyzed data from two studies patients with new‐ recent‐onset T1D. At...
Laboratory testing is routinely used to assay blood biomarkers provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos additional value in understanding disease states and common results.We developed EchoNet-Labs, a video-based algorithm detect evidence anemia, elevated B-type natriuretic peptide (BNP), troponin I, urea nitrogen (BUN), as well values ten lab...
Background High blood pressure affects approximately 116 million adults in the United States. It is leading risk factor for death and disability across world. Unfortunately, over past decade, hypertension control rates have decreased Prediction models clinical studies shown that reducing clinician inertia alone sufficient to reach target of ≥80% control. Digital health tools containing evidence‐based algorithms are able reduce a good fit turning tide control, but careful consideration should...
Cardiac wall motion abnormalities (WMA) are strong predictors of mortality, but current screening methods using Q waves from electrocardiograms (ECGs) have limited accuracy and vary across racial ethnic groups. This study aimed to identify novel ECG features deep learning enhance WMA detection, referencing echocardiography as the gold standard. We collected echocardiogram data 35,210 patients in California labeled unstructured language parsing echocardiographic reports. A neural network...
Sodium/hydrogen exchangers (NHEs) play a major role in Na(+) absorption, cell volume regulation, and intracellular pH regulation. Of the nine identified mammalian NHEs, three (NHE2, NHE3, NHE8) are localized on apical membrane of epithelial cells small intestine kidney. Although regulation NHE2 NHE3 expression has been extensively studied past decade, little is known about NHE8 gene under physiological conditions. The current studies were performed to explore epidermal growth factor (EGF)...
<h3>Objective:</h3> To determine by ultrasound (US) the spinal canal depth (SCD) in neonates and subsequently establish a nomogram simple formula for calculating this distance. <h3>Design:</h3> 116 US measurements were performed two investigators 105 at L3/4 intervertebral space. Both anterior posterior measured mid-spinal (MSCD) calculated. Measurements of intra- interobserver variability also performed. <h3>Results:</h3> A clear relationship was found between body weight (W, kg) all SCD...
Abstract Laboratory blood testing is routinely used to assay biomarkers provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos additional value in understanding disease states and predict common results. Using 70,066 echocardiograms associated biomarker results 39,460 patients, we developed EchoNet-Labs, a video-based algorithm anemia, elevated B-type...
Fis1 mediates mitochondrial and peroxisomal fission. It is tail-anchored to these organelles by a transmembrane domain, exposing soluble cytoplasmic domain. Previous studies suggested that autoinhibited its N-terminal region. Here, 1.75 Å resolution crystal structure of the domain from Saccharomyces cerevisiae reported which adopts tetratricopeptide-repeat fold. observed this fold creates concave surface important for fission, but sterically occluded Thus, provides physical basis...
Abstract Background Cardiovascular disease is the leading cause of morbidity and mortality in patients with chronic kidney ( CKD ). In fact, death from cardiovascular number one graft loss transplant KT x) patients. Compared to on dialysis, x have increased quality length life. It not known, however, whether outcomes coronary artery bypass CABG ) surgery differ between or dialysis. Methods This was a retrospective cohort study comparing dialysis undergoing included Nationwide Inpatient...
Abstract Importance Deep learning methods have recently gained success in detecting left ventricular systolic dysfunction (LVSD) from electrocardiogram waveforms. Despite their impressive accuracy, they are difficult to interpret and deploy broadly the clinical setting. Objective To determine whether simpler models based on standard measurements could detect LVSD with similar accuracy deep models. Design Using an observational dataset of 40,994 matched 12-lead electrocardiograms (ECGs)...
Abstract Aims Deep learning methods have recently gained success in detecting left ventricular systolic dysfunction (LVSD) from electrocardiogram (ECG) waveforms. Despite their high level of accuracy, they are difficult to interpret and deploy broadly the clinical setting. In this study, we set out determine whether simpler models based on standard ECG measurements could detect LVSD with similar accuracy that deep models. Methods results Using an observational data 40 994 matched 12-lead...
Abstract Background Detection of prior myocardial infarction (MI) may inform arrhythmia treatment and prognosis, yet cardiac imaging is resource intensive. ECG Q-wave analysis quick inexpensive but has poor accuracy for assessing MI. Purpose To evaluate the ability a deep neural network (DNN) trained on surface to identify patients with Methods We assessed 608 well-characterized (61.4±14.5 years, 31.2% female) at 2 academic centers. From one 12-lead ECG, median beats were calculated in 3...
A 75-year-old woman presented for evaluation of exertional syncope. Her electrocardiogram (ECG) is shown in Figure 1. Representative tracings from her exercise treadmill study are 2. Based on review the Figures 1 and 2, predict site atrioventricular (AV) block.Figure 2Electrocardiogram during exercise. A: Beginning B: During C: recovery.View Large Image ViewerDownload Hi-res image Download (PPT) presenting ECG shows sinus rhythm at 90 bpm with 2:1 AV block ventricular rate 45 bpm, PR...
Background: Cardiac wall motion abnormalities (WMA) independently predict mortality and other adverse events beyond ejection fraction. Clinical screening relies on detection of ECG Q waves yet has poor predictive accuracy. Hypothesis: We hypothesized that features the wave could be identified by deep learning to improve WMA over standard measurements. Methods: collected ECGs echocardiogram pairs (Panel A) in 35,210 unique patients who underwent both studies within 60 days at Stanford...
Clinical screening of myocardial infarction is important for preventative treatment and risk stratification in cardiology practice, however current detection by electrocardiogram Q-wave analysis provides only modest accuracy assessing prior cardiac events. We set out to evaluate the ability a deep neural network trained on identify patients with clinical history infarction. assessed 608 at two academic centers adjudicated Surface electrocardiograms were used train network-based model that...