Be the first to attend this event.
AI applications are developed on vast amounts of data. In healthcare, the quality of that data, and the types of data being used to train the algorithm, are critical. Whilst AI isn’t intrinsically biased, if the data used to create these algorithms doesn’t contain a diverse representation of society in terms of ethnicity, age, geography and gender, they cannot produce accurate, generalisable outputs.
For example, the incidence rate of breast cancer for Black women is close to that of white women. However, the mortality rates are markedly different, with Black women having a 40% higher death rate from breast cancer, according to data compiled by the American Cancer Society. Possible risk factors for this include socioeconomic status, biological and genetic differences in tumors and differential access to healthcare. AI has the potential to revolutionise healthcare but precautions must be taken to ensure we are eliminating rather than perpetuating these kinds of biases.
Join this session to hear from leading experts as they discuss the importance of generalisability in healthcare and how the rapid adoption of AI means that it is critical that stakeholders take steps to address algorithmic biases now.
Speakers:
Dr. Bonnie Joe, MD, PhD - Chief of Breast Imaging, UCSF
Dr. Amy Patel, MD - Medical Director of The Breast Care Center at Liberty Hospital & Assistant Professor of Radiology, University of Missouri-Kansas City School of Medicine
Dr. Hari Trivedi, MD - Assistant Professor of Radiology and Biomedical Informatics, Emory University
Sarah Kerruish - Chief Strategy Officer, Kheiron Medical Technologies (Moderator)
McCormick Place, 2301 South King Drive, Chicago, IL 60616