Invited Speakers

AI for AI-readiness:
Facilitating scientific discovery by cleaning up our metadata mess
Monday, May 16, 2022, 9:15 - 10:15, Leatherback

Mark A. Musen

Professor of Biomedical Informatics and Biomedical Data Science, Stanford University
Abstract: Scientists dream of using AI to sift though existing data sets to make new discoveries. They imagine students with laptops poring through online data and stumbling on the next remdesivir to treat COVID. Unfortunately, despite increasing requirements for data sharing and open science, real-world scientific data are almost never in a form that enables third parties to make sense of what the original investigators have done. The problem is that the metadata that scientists create to describe their data sets are, in most cases, unusable. Although workers in AI may take it for granted that their approaches will advance science simply through the availability of the myriad data sets in the public domain, that vision will not pan out until scientific metadata becomes more useful. There are great opportunities for AI to help investigators to clean up legacy metadata to make existing datasets more understandable, and also to help investigators to create good metadata in the first place. The Metadata Powerwash converts existing metadata to a form that is more searchable and interpretable. The CEDAR Workbench helps scientists to use formal reporting guidelines and terms from standard ontologies to create high-quality metadata de novo. These tools demonstrate how AI approaches can be helpful to ensure that scientific data are processable and interpretable by both humans and machines..
Bio: Dr. Musen is Professor of Biomedical Informatics and Biomedical Data Science at Stanford University, where he is Director of the Stanford Center for Biomedical Informatics Research. Dr. Musen conducts research related to intelligent systems, reusable ontologies, metadata for annotation of scientific data sets, and biomedical decision support. His long-standing work on the Protégé system has led to widely used, open-source technology to build ontologies and intelligent computer systems. In the 1990s, he pioneered work on the engineering of intelligent systems by using domain ontologies to structure symbolic knowledge bases, and by mapping those knowledge bases to reusable problem-solving services. More recently, he has focussed on the application of AI to problems in open science. He is principal investigator of BioPortal ontology repository as well as the Center for Expanded Data Annotation and Retrieval (CEDAR), which applies semantic technology to enhance the metadata used to annotate scientific data sets.

The Era of Human-Robot Collaboration: Deep-Sea Robotics Exploration
Tuesday, May 17, 2022, 9:15 - 10:15, Leatherback

Oussama Khatib

Stanford University
Abstract: The promise of oceanic discovery has intrigued scientists and explorers, whether to study underwater ecology and climate change, or to uncover natural resources and historic secrets buried deep at archaeological sites. This quest to explore the oceans requires expert human access, but much of the oceans is inaccessible to humans. Reaching these depths is imperative for understanding the ecology, maintaining, and repairing underwater structures, and working in archaeological sites over this immensely unknown part of our planet. This challenge demands human‐level abilities at depths where humans cannot or should not be. Ocean One was conceived to create a robotic diver with a high degree of autonomy for physical interaction with the environment while connected to a human expert through an intuitive interface. The robot was deployed in an expedition in the Mediterranean to King Louis XIV’s flagship Lune, lying off the coast of Toulon at ninety‐one meters. The discussion focuses on the development of a new prototype, OceanOneK, with the ability to reach 1000 meters. Distancing humans physically from dangerous and unreachable spaces while connecting their skills, intuition, and experience to the task promises to fundamentally alter remote work. These development show how human‐robot collaboration induced synergy can expand our abilities to reach new resources, build and maintain infrastructure, and perform disaster prevention and recovery operations ‐ be it deep in oceans and mines, at mountain tops, or in space.
Bio: Oussama Khatib received his PhD from Sup’Aero, Toulouse, France, in 1980. He is Professor of Computer Science and Director of the Robotics Laboratory at Stanford University. His research focuses on methodologies and technologies in human-centered robotics, haptic interactions, artificial intelligence, human motion synthesis and animation. He is President of the International Foundation of Robotics Research (IFRR) and a Fellow of the Institute of Electrical and Electronic Engineers (IEEE). He is Editor of the Springer Tracts in Advanced Robotics (STAR) series, and the Springer Handbook of Robotics, awarded the American Publishers Award for Excellence in Physical Sciences and Mathematics. He is recipient of the IEEE Robotics and Automation (IEEE/RAS) Pioneering Award (for his fundamental contributions in robotics research, visionary leadership and life-long commitment to the field), the IEEE/RAS George Saridis Leadership Award, the Distinguished Service Award, the Japan Robot Association (JARA) Award, the Rudolf Kalman Award, and the IEEE Technical Field Award. Professor Khatib is a member of the National Academy of Engineering.

Towards a novel ecosystem for transparent integration of Artificial Intelligence in clinical flow
Wednesday, May 18, 2022, 9:00 - 10:00, Leatherback

Yelena Yesha

University of Miami, Institute for Data Science & Computing
Abstract: Artificial intelligence (AI)- and machine learning (ML)-based technologies have the potential to transform healthcare by deriving new and essential insights from the vast amount of data generated during the delivery of healthcare every day. Example high-value applications include earlier disease detection, more accurate diagnosis, identification of new observations or patterns on human physiology, and development of personalized diagnostics and therapeutics. One of the most significant benefits of AI/ML in software resides in its ability to learn from real-world use and experience and its capability to improve its performance. The ability for AI/ML software to learn from real-world feedback (training) and improve its performance (adaptation) makes these technologies uniquely situated among software as a medical device (SaMD) and a rapidly expanding area of research and development. While the FDA has made significant strides in developing appropriately tailored policies for SaMD to ensure the safe and effective technologies reach users, we believe that the next paradigm for device regulation needs to be ready for adaptive AI/ML technologies, which have the potential to adapt and optimize device performance in real-time to improve healthcare for patients continuously. Such change requires an approach based on a new technological ecosystem allowing for continuous testing and following of AI-based devices that facilitates a rapid product improvement cycle and allows these devices to improve continually while providing adequate safeguards.We present here the basis of a novel ecosystem developed between the WVU, Rockefeller Neuroscience Institute and the UMiami Institute for Data Science and Computing (IDSC). This Consortium brings together multidisciplinary expertise in large radiology systems, medical imaging analytics, large clinical data management, ML/AI, radiomics, real-world evidence collection, and regulatory and access to extensive clinical flow and data.The framework is based on three pillars: 1) seamless access of de-identified clinical data from radiology and medical records allowing for preliminary training of novel analytics models, 2) low footprint compliant integration of AI models in the radiological clinical flow, 3) gathering of information and monitoring of performances in conjunction with radiologists and clinical professionals. We conclude with the presentation of opportunities of such systems to support continuous and AI-based regulatory frameworks.
Bio: At the University of Miami, Dr. Yelena Yesha is the Knight Foundation Endowed Chair of Data Science and AI at the Institute for Data Science and Computing (IDSC). At IDSC, Dr. Yesha is also the Innovation Officer and Head of International Relations. In this role, Dr. Yesha assists faculty in engaging government and industrial partners to collaborate with the University and consults with faculty on developing research ideas into innovations.Dr. Yesha was the Founding Director of the National Science Foundation Center for Accelerated Real Time Analytics (CARTA), an NSF-funded Industry/University Cooperative Research Center (I/UCRC) that aims to develop long-term partnerships among industry, academia, and government. CARTA partners with Rutgers University New Brunswick, North Carolina State University, the University of Maryland Baltimore County (UMBC), Tel Aviv University, and the University of Miami.Dr. Yesha received her B.Sc. degrees in Computer Science and in Applied Mathematics from York University, Toronto, Canada, and her M.Sc. degree and Ph.D. degree in Computer Science from The Ohio State University She has published 11 books as author or editor, and more than 200 papers in prestigious refereed journals and refereed conference proceedings, and she has been awarded external funding in a total amount exceeding 45 million dollars. She is currently working with leading industrial companies and government agencies on new innovative technology in the areas of blockchains, cybersecurity, and big data analytics with applications to electronic commerce, climate change, and digital healthcare. Dr. Yesha is a fellow of the IBM Centre for Advanced Studies.