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.
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.
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.
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.
EchoNet-POCUS can be applied to bedside echocardiogram videos in real time using commodity hardware, as we demonstrate in a prospective pilot study.
To read this article in full you will need to make a payment
Purchase one-time access:Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
One-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:Subscribe to Journal of Emergency Medicine
Already a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
- Manual of emergency and critical care ultrasound.Cambridge University Press, Cambridge, UK2011
- Point-of-care ultrasonography (POCUS) in a community emergency department: an analysis of decision making and cost savings associated with POCUS.J Ultrasound Med. 2019; 38: 2133-2140
- Ultrasonography in the emergency department.Crit Care. 2016; 20: 227
- Point-of-care ultrasound in primary care: a systematic review of generalist performed point-of-care ultrasound in unselected populations.Ultrasound J. 2019; 11: 31
- Point-of-care ultrasound in intensive care units: assessment of 1073 procedures in a multicentric, prospective, observational study.Intensive Care Med. 2015; 41: 1638-1647
- The oblique view: an alternative approach for ultrasound-guided central line placement.J Emerg Med. 2009; 37: 403-408
- Variability in ultrasound education among emergency medicine residencies.West J Emerg Med. 2010; 11: 314-318
- Dedicated time for deliberate practice: one emergency medicine program's approach to point-of-care ultrasound (PoCUS) training.CJEM. 2015; 17: 558-561
- Emergency department point-of-care ultrasound in out-of-hospital and in-ED cardiac arrest.Resuscitation. 2016; 109: 33-39
- Recommendations for echocardiography laboratories participating in cardiac point of care cardiac ultrasound (POCUS) and critical care echocardiography training: report from the American Society of Echocardiography.J Am Soc Echocardiogr. 2020; 33 (e4): 409-422
- Assessing left ventricular systolic function by emergency physician using point of care echocardiography compared to expert: systematic review and meta-analysis.Eur J Emerg Med. 2022; 29: 18-32
- Deep learning evaluation of biomarkers from echocardiogram videos.EBioMedicine. 2021; 73103613
- Fast and accurate view classification of echocardiograms using deep learning.NPJ Dig Med. 2018; 1 (Available atAccessed March 8, 2023): 6https://doi.org/10.1038/s41746-017-0013-1
- Video-based AI for beat-to-beat assessment of cardiac function.Nature. 2020; 580: 252-256
- Fully automated echocardiogram interpretation in clinical practice.Circulation. 2018; 138: 1623-1635
- A closer look at spatiotemporal convolutions for action recognition.in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT. June 2018https://doi.org/10.1109/cvpr.2018.00675 (Available atAccessed Xxxx XX, 202X)
- Accuracy of left ventricular ejection fraction by contemporary multiple gated acquisition scanning in patients with cancer: comparison with cardiovascular magnetic resonance.J Cardiovasc Magn Reson. 2017; 19: 34
- Heart failure incidence and survival (from the Atherosclerosis Risk in Communities study).Am J Cardiol. 2008; 101: 1016-1022
- PyTorch: an imperative style, high-performance deep learning library.(Wallach H, Larochelle H, Beygelzimer A, d'Alché-Buc F, Fox, Garnett R, eds)Advances in neural information processing systems. 32. Curran Associates, Inc., 2019 (Available at)Accessed Xxxx XX, 202X)
Published online: February 24, 2023
Accepted: February 17, 2023
Received in revised form: January 11, 2023
Received: July 20, 2022
Publication stageIn Press Uncorrected Proof
© 2023 Elsevier Inc. All rights reserved.