Bias, Equity, and Reality: Issues When Using AI for ECG-based Diagnostics

Bias, Equity, and Reality: Issues When Using AI for ECG-based Diagnostics

Guests: Gari Clifford, Ph.D. @GariClifford and Reza Sameni, Ph.D. @RezaSameni

Hosts: Anthony H. Kashou, M.D. (@anthonykashoumd)

Joining us today to discuss issues when using AI for ECG-based diagnostics is Gari Clifford, Ph.D., Chair of Biomedical Informatics at Emory University and professor of Biomedical Engineering at Georgia Institute of Technology, and Reza Sameni, Ph.D., associate professor of the department of Biomedical Informatics at Emory University. Drs. Clifford and Sameni share interests in machine learning, digital hardware design, statistical signal processing and application areas span across cardiovascular disease, neuropsychiatric health, among others. Tune in to learn about issues when using AI for ECG-based diagnostics.

Specific topics discussed:

• What are the key barriers to building AI models from electrocardiogram data?
• What can be done to mitigate the bias in AI models beyond balancing data.
• Can you expand on what you mean by addressing bias is much deeper than just balancing data?
• What parting advice do you have for anyone wanting to use AI on large volumes of ECGs?

Connect with Mayo Clinic's Cardiovascular Continuing Medical Education online at https://cveducation.mayo.edu or on Twitter @MayoClinicCV and @MayoCVservices.

Facebook: MayoCVservices

LinkedIn: Mayo Clinic Cardiovascular Services

NEW Cardiovascular Education App:
The Mayo Clinic Cardiovascular CME App is an innovative educational platform that features cardiology-focused continuing medical education wherever and whenever you need it. Use this app to access other free content and browse upcoming courses. Download it for free in Apple or Google stores today!

No CME credit offered for this episode.

Podcast episode transcript found here.