top of page

BackTable / VI / Podcast / Episode #251

Race and AI in Radiology

with Dr. Judy Gichoya

In this episode, Dr. Ally Baheti interviews interventional radiologist Dr. Judy Gichoya about her recent paper on artificial intelligence (AI) and the use of a deep learning model to recognize patients’ self-described racial identity, based on radiology images.

Sponsored by:

Medtronic Concerto

Be part of the conversation. Put your sponsored messaging on this episode. Learn how.

Race and AI in Radiology with Dr. Judy Gichoya on the BackTable VI Podcast)
Ep 251 Race and AI in Radiology with Dr. Judy Gichoya
00:00 / 01:04

BackTable, LLC (Producer). (2022, October 14). Ep. 251 – Race and AI in Radiology [Audio podcast]. Retrieved from https://www.backtable.com

Free CME

Reflect on how this Podcast applies to your day-to-day and earn free AMA PRA Category 1 CMEs. Follow the button below to claim your credits on CMEfy.

BackTable CMEfy button

Stay Up To Date

Follow:

Subscribe:

Sign Up:

Podcast Contributors

Dr. Judy Gichoya discusses Race and AI in Radiology on the BackTable 251 Podcast

Dr. Judy Gichoya

Dr. Judy Gichoya is an interventional radiologist, researcher, and assistant professor at Emory University School of Medicine.

Dr. Aparna Baheti discusses Race and AI in Radiology on the BackTable 251 Podcast

Dr. Aparna Baheti

Dr. Aparna Baheti is a practicing Interventional Radiologist in Tacoma, Washington.

Show Notes

Dr. Gichoya had started by tackling the original problem of bias in diagnoses for chest X-rays, since it has always been difficult to tell whether something is a real diagnosis, or simply just a finding. Her team built a deep learning model; however, they saw that it did not work well for black patients. With further investigation, they discovered that their model had learned signals that correlated with self-identified race.

Intrigued by this finding, Dr. Gichoya and her team sought to identify the factors that the model used when making its race determination. Because AI is black box in nature, the methods by which the algorithm learns remains largely unknown. When tested in other imaging modalities (mammogram, chest CT, spine imaging), the model still showed high accuracy. Additionally, the model retained accuracy when different information was eliminated from the images (ex. age, disease distributions, bone densities). The model was also able to predict race in healthy patients, showing that it did not rely on patterns of disease prevalence in specific ethnic groups.

Next, we spoke about the implications of this research in developing risk scores. Deep learning models are able to look at factors that humans are not trained or able to see. Dr. Gichoya highlights the model’s potential effectiveness in predicting osteoarthritis risk in black patients. We also look at applications in opportunistic screening and information about social determinants of health. For example, most patients presenting with chest pain often get chest CTs. Dr. Gichoya thinks that these images can be used by the model to learn about patients’ environmental exposures, like pollution.

We finish the episode with a discussion on the changing landscape of IR and how AI can be used as an assistive technology. Interventional cardiologists are already using AI to dictate their procedural reports in real-time. In the interventional oncology space, AI could help integrate imaging and pathology findings to determine personalized treatment courses. All of these applications depend on researchers’ ability to market their findings to peers and the public, Dr. Gichoya gives tips on how to do this.

Resources

AI recognition of patient race in medical imaging: a modelling study:
https://www.thelancet.com/journals/landig/article/PIIS2589-7500(22)00063-2/fulltext

Disclaimer: The Materials available on BackTable.com are for informational and educational purposes only and are not a substitute for the professional judgment of a healthcare professional in diagnosing and treating patients. The opinions expressed by participants of the BackTable Podcast belong solely to the participants, and do not necessarily reflect the views of BackTable.

backtable-earn-free-cme.jpg
backtable-plus-vi-cta.jpg
Become a BackTable Sponsor

Up Next

Tunneled Pleural and Peritoneal Catheters with Dr. Ally Baheti and Dr. Chris Beck on the BackTable VI Podcast)
Iliofemoral Stenting: Decision-Making & Best Practices Explored with Dr. Kush Desai and Dr. Steven Abramowitz on the BackTable VI Podcast)

Articles

Topics

Get in touch!

We want to hear from you. Let us know if you’re interested in partnering with BackTable as a Podcast guest, a sponsor, or as a member of the BackTable Team.

Select which show(s) you would like to subscribe to:

Thanks! Message sent.

bottom of page