AI Article Synopsis
- The study focuses on the use of point-of-care ultrasound (POCUS) to improve assessments of unstable patients in emergency departments, particularly through echocardiograms to evaluate heart function.
- A new deep learning system named EchoNet-POCUS was developed to help emergency physicians interpret echocardiogram videos and minimize variability between operators.
- Results show EchoNet-POCUS has high accuracy in predicting abnormal cardiac function (AUROC of 0.92) and decent accuracy in evaluating video quality (AUROC of 0.81), demonstrating its potential for real-time application in clinical settings.
Article Abstract
Background: The adoption of point-of-care ultrasound (POCUS) has greatly improved the ability to rapidly evaluate unstable emergency department (ED) patients at the bedside. One major use of POCUS is to obtain echocardiograms to assess cardiac function.
Objectives: We developed EchoNet-POCUS, a novel deep learning system, to aid emergency physicians (EPs) in interpreting POCUS echocardiograms and to reduce operator-to-operator variability.
Methods: We collected a new dataset of POCUS echocardiogram videos obtained in the ED by EPs and annotated the cardiac function and quality of each video. Using this dataset, we train EchoNet-POCUS to evaluate both cardiac function and video quality in POCUS echocardiograms.
Results: EchoNet-POCUS achieves an area under the receiver operating characteristic curve (AUROC) of 0.92 (0.89-0.94) for predicting whether cardiac function is abnormal and an AUROC of 0.81 (0.78-0.85) for predicting video quality.
Conclusions: EchoNet-POCUS can be applied to bedside echocardiogram videos in real time using commodity hardware, as we demonstrate in a prospective pilot study.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jemermed.2023.02.005 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Mechanism-guided engineering of a minimal biological particle for genome editing.
Proc Natl Acad Sci U S A
January 2025
Innovative Genomics Institute, University of California, Berkeley, CA 94720.
The widespread application of genome editing to treat and cure disease requires the delivery of genome editors into the nucleus of target cells. Enveloped delivery vehicles (EDVs) are engineered virally derived particles capable of packaging and delivering CRISPR-Cas9 ribonucleoproteins (RNPs). However, the presence of lentiviral genome encapsulation and replication proteins in EDVs has obscured the underlying delivery mechanism and precluded particle optimization.
View Article and Find Full Text PDFThe development of preterm infants from low socio-economic status families: The combined effects of melatonin, autonomic nervous system maturation and psychosocial factors (ProMote): A study protocol.
PLoS One
January 2025
Department of Neonatology/Neonatal Intensive Care Unit, University Hospital of Heraklion, School of Medicine, University of Crete, Heraklion, Crete, Greece.
Preterm births constitute a major public health issue and a chronic, cross-generational condition globally. Psychological and biological factors interact in a way that women from low socio-economic status (SES) are disproportionally affected by preterm delivery and at increased risk for the development of perinatal mental health problems. Low SES constitutes one of the most evident contributors to poor neurodevelopment of preterm infants.
View Article and Find Full Text PDFMuscle relaxation enhances motor imagery capacity in people with anxiety: A randomized clinical trial.
PLoS One
January 2025
Department of Nursing and Physiotherapy, Faculty of Medicine and Health Sciences, University of Alcalá, Alcalá de Henares, Spain.
Background: Motor imagery is the mental representation of a movement without physical execution. When motor imagery is performed to enhance motor learning and performance, participants must reach a temporal congruence between the imagined and actual movement execution. Identifying factors that can influence this capacity could enhance the effectiveness of motor imagery programs.
View Article and Find Full Text PDFUnsupervised clustering of intraventricular hemodynamic forces for the phenotyping of left-ventricular function in non-ischemic left ventricular cardiomyopathy.
Eur Heart J Cardiovasc Imaging
January 2025
Vall d'Hebron Research Institute (VHIR), Barcelona, Spain.
Background: Cardiac magnetic resonance (CMR) is essential for diagnosing cardiomyopathy, serving as the gold standard for assessing heart chamber volumes and tissue characterization. Hemodynamic forces (HDF) analysis, a novel approach using standard cine CMR images, estimates energy exchange between the left ventricular (LV) wall and blood. While prior research has focused on peak or mean longitudinal HDF values, this study aims to investigate whether unsupervised clustering of HDF curves can identify clinically significant patterns and stratify cardiovascular risk in non-ischemic LV cardiomyopathy (NILVC).
View Article and Find Full Text PDFThe Effectiveness and Safety of Beta Antagonists in Patients With Burns: An Updated Meta-Analysis.
Am Surg
January 2025
Department of Medicine, Ziauddin Medical College, Karachi, Pakistan.
Aims: The purpose of this systematic review was to assess the safety and effectiveness of beta antagonists for improving clinical care in burn patients, compared to placebo.
Methods: Articles from randomized-controlled trials were identified by a literature search on PubMed and Cochrane. We included relevant trials involving patients with burn.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!