SCCM Resource Library-Prospective Real-Time Validation of a Lung Ultrasound Deep Learning Model in the Intensive Care Unit

Prospective Real-Time Validation of a Lung Ultrasound Deep Learning Model in the Intensive Care Unit

Video Transcription

Video Summary

In this video, Chintan Davey presents his research on using artificial intelligence to automate lung ultrasound interpretation in acute care settings. He explains that lung ultrasound has high diagnostic accuracy but is underutilized due to a lack of experts. Therefore, he and his team created a deep learning model to distinguish between normal and abnormal lung ultrasound images. The model was trained on over 270,000 images and tested on over 1,000 ultrasound clips. It performed well on both local and external data sets, with an AUC of 96% and 92.4% respectively. The model was then applied in a real-life ICU environment and demonstrated high accuracy. These findings suggest that AI can be incorporated into clinical care for critically ill patients.

Asset Subtitle

Quality and Patient Safety, Procedures, 2023

Asset Caption

Type: star research | Star Research Presentations: Pulmonary (SessionID 30004)

Meta Tag

Content Type Presentation

Knowledge Area Quality and Patient Safety

Knowledge Area Procedures

Membership Level Professional

Membership Level Select

Tag Evidence Based Medicine

Tag Ultrasound

Year 2023

Keywords

artificial intelligence

lung ultrasound interpretation

acute care settings

deep learning model

diagnostic accuracy

	Society of Critical Care Medicine 500 Midway Drive Mount Prospect, IL 60056 USA Phone: +1 847 827-6888 Fax: +1 847 439-7226 Email: support@sccm.org	Contact Us About SCCM Newsroom Advertising & Sponsorship DONATE	MySCCM LearnICU Patients & Families Surviving Sepsis Campaign Critical Care Societies Collaborative	GET OUR NEWSLETTER
© Society of Critical Care Medicine. All rights reserved. \| Privacy Statement \| Terms & Conditions The Society of Critical Care Medicine, SCCM, and Critical Care Congress are registered trademarks of the Society of Critical Care Medicine.