Translation of Clinical Imaging AI: Solving The Day Two Problem
Matthew Lungren
August 24, 2022, Wednesday, 3:00 PM - 4:00 PM EST
Rapidly expanding Clinical AI applications worldwide have the potential to impact to all areas of medical practice. Medical imaging applications constitute a vast majority of approved clinical AI applications with more than 150 to date. Though healthcare systems are eager to adopt AI solutions, fundamental questions remain regarding governance, decisions on which model to choose, who should make the decision, and more. Further, after deployment, more questions arise: Is the model still working as expected?, What is causing the change?, Is it time to intervene? This talk will cover the latest thinking on medical imaging AI governance, strategies and pitfalls, as well as new research in the area of how to monitor input data and track model performance of models after deployment to ensure they remain safe and effective for our patients.
Matt Lungren is the Chief Medical Information Officer at Nuance, a Microsoft Company. He also holds affiliate positions with UCSF, Duke, and Stanford University. Prior to joining AWS, Dr Lungren was an interventional radiologist and research faculty at Stanford University Medical School where he led the Stanford Center for Artificial Intelligence in Medicine and Imaging (AIMI). His work has led to more than 100 scientific publications, including work on multi-modal data fusion models for healthcare applications, new computer vision and natural language processing approaches for healthcare specific domains, opportunistic screening with machine learning for public health applications, open medical data as public good, and prospective clinical trials for clinical AI translation. He served as advisor for early stage startups and large fortune-500 companies on healthcare AI go-to-market strategy. As a top rated instructor on Coursera, his course Fundamentals of Machine Learning in Healthcare, designed especially for learners with clinical non-technical backgrounds, has been completed by more than 11k students around the world.