false
OasisLMS
Catalog
ASGE Annual Postgraduate Course: Clinical Challeng ...
Learning from Other Disciplines: How Far Behind is ...
Learning from Other Disciplines: How Far Behind is GI?
Back to course
[Please upgrade your browser to play this video content]
Video Transcription
Video Summary
In this video, Dr. Charles Kahn, a professor and vice chair of radiology at the University of Pennsylvania, discusses the challenges and considerations of implementing artificial intelligence (AI) in medical imaging. He highlights the importance of data quality and training standards, using examples of AI systems detecting pneumonia and tuberculosis, as well as racial bias in image analysis. He emphasizes the need for rigorous testing and validation of AI systems, particularly in different healthcare settings, to ensure their accuracy and usefulness. Dr. Kahn also mentions the importance of information standards, such as DICOM, in enabling interoperability and innovation in radiology. He recommends the use of checklists and guidelines, such as the CLAIM and ECLAIR guidelines, to evaluate and integrate commercial AI solutions into clinical workflows. Dr. Kahn concludes by expressing the need for continued collaboration and improvement in AI applications across medical specialties.
Asset Subtitle
Charles Kahn, Jr., MD, MS
Keywords
artificial intelligence
medical imaging
data quality
racial bias
clinical workflows
×
Please select your language
1
English