2023-10-21, 11:40–12:10 (Europe/Athens), Α115-117
Repeated stories of AI trained on selected populations but failing in real world scenarios demonstrate the existing shortcomings in production-grade healthcare AI, and more importantly, highlight the disconnection among research hubs and community medical practices. In this talk we will be presenting MedPerf (http://medperf.org), an open-source platform for open & reproducible benchmarking of medical AI, at global scale, to help mitigate selected challenges via federation, best practices, and shared data choices.
Alexandros Karargyris co-chairs the Medical working group at MLCommons. The group has a mission to provide neutral benchmarking and best practices for Medical AI in an effort to circumvent negative effects of AI. In its short life span the group has grown to already support the largest federation of brain tumor segmentation as well as to plan its prospective AI studies. Previously he worked as a research lead at IHU Strasbourg in projects related to applications in the intersection of surgery and AI. He also worked as a researcher at IBM and NIH for more than 10 years. His research interests lie in the space of medical imaging, machine learning and mobile health. He has contributed to healthcare commercial products and imaging solutions deployed in under-resourced areas. His research has been published in peer-reviewed journals and conferences.