Keynote Speakers
DR. Andreas Holzinger
Human-Centered AI Lab, Institute of Medical Informatics and Statistics,
Medical University Graz, Austria
Medical University Graz, Austria
Title: Explainability and Robustness in Health Intelligence
Abstract: Expectations for health intelligence systems are high, particularly in disciplines that require prognostic models (oncology) and/or decision support, including pathology, radiology, dermatology. Advances in statistical machine learning, the availability of large amounts of training data, and increasing computational power have made AI successful. In certain medical tasks it even achieves human-level performance. To become even more successful, AI solutions still need two “ingredients”, i.e., explainability and robustness. Explainability is already a must, as e.g., the European Union imposes legal conditions that require replicability, explainability and transparency. Lacking robustness means that our best performing models are very sensitive, i.e., small perturbations in the input data can have dramatic consequences in the output. This is relevant because in medicine, lack of data quality is one of the main challenges as we rarely have i.i.d data available. One possible step to overcome this problem is to combine statistical learning with knowledge representations. For certain tasks, it may be advantageous to use a human-in-the-loop. The human expert can - sometimes, not always - contribute experience and conceptual understanding. Such approaches are not only a solution from a legal point of view, but in medicine the "why" is often more important than a pure classification result. Traceability and interpretability can promote reliability and trust and ensure that humans remain in control, thus complementing human intelligence with artificial intelligence and, most importantly, and ensures the human-in-control.
Short Biography: Andreas Holzinger is lead of the Human-Centered AI Lab at the Medical University Graz, Austria. Currently, he is Visiting Professor for explainable AI at the Alberta Machine Intelligence Institute of the University of Alberta, Edmonton, Canada, and since 2016 he is Visiting Professor for machine learning in health informatics at Vienna University of Technology. Andreas serves as consultant for the Canadian, US, UK, Swiss, French, Italian and Dutch governments, for the German Excellence Initiative, and as national expert in the European Commission. He is in the advisory board of the Artificial Intelligence Strategy “AI Made in Germany 2030” of the German Federal Government. Andreas promotes a synergistic approach to Human-Centred AI and has pioneered in interactive machine learning (iML) with the human-in-the-loop. For his pioneer work he was elected as full member to the Academia Europaea, the European Academy of Science. Andreas obtained a Ph.D. in Cognitive Science from Graz University in 1998 and his second Ph.D. in Computer Science from TU Graz in 2003. He serves as Austrian Representative for AI in IFIP TC 12, and is member of IFIP WG 12.9 Computational Intelligence, the ACM, IEEE, the German Informatics Society, and the AAAI. (More information: https://www.aholzinger.at)
Assistant Professor, Computational Wellbeing Group,
Department of Electrical and Computer Engineering, Rice University, Texas, USA
Department of Electrical and Computer Engineering, Rice University, Texas, USA
Title: Digital Health and Wellbeing: Data-Driven and Human-Centered Personalized and Adaptive Assistant
Abstract: Imagine 24/7 rich human multimodal data could identify changes in physiology and behavior, and provide personalized early warnings to help you, patients, or clinicians for making better decisions or behavioral changes to support health and wellbeing. I will introduce a series of studies, algorithms, and systems we have developed for measuring, predicting, and supporting personalized health and wellbeing for clinical populations as well as people at increased risk of adverse events, including ongoing COVID-19 related projects. I will also discuss challenges, learned lessons, and potential future directions in digital health and wellbeing research.
Short Biography: Akane Sano is an Assistant Professor at Rice University, Department of Electrical Computer Engineering, Computer Science, & Bioengineering. She directs Computational Wellbeing Group. She is also a member of Rice Scalable Health Labs. Her research focuses on affective, ubiquitous, and wearable computing, and biobehavioral sensing and analysis/modeling. Her research targets (1) the analysis and modeling of human ambulatory multimodal time-series data including physiological, biological, and behavioral data for measuring, predicting, improving, and understanding human physiology and behavior and human factors such as health, wellbeing, and performance and (2) development of human-centered computing technologies to support health and wellbeing. She received her Ph.D. at MIT. Before she came to the US, she was a researcher/engineer at Sony Corporation and worked on affective/wearable computing, intelligent systems, and human-computer interaction. Her recent awards include Microsoft Productivity Research Award in 2019, the Best Paper Award at IEEE BHI 2019 conference, the Best Paper Award at the NIPS 2016 Workshop on Machine Learning for Health, and the 2014 AAAI Spring Symposium Best Presentation Award.
IBM Fellow, IBM Fellow, IBM Research - Almaden Distinguished Fellow,
AIMI Center, Stanford University, CA, USA
AIMI Center, Stanford University, CA, USA
Title: The Medical Sieve Radiology Grand Challenge on Chest X-rays
Abstract: With the promise of AI, the task of automating preliminary read reports for common exams such as chest X-rays to expedite clinical workflows and improve operational efficiencies in hospitals appear likely. The Medical Sieve Grand Challenge was an ambitious attempt to reach this capability which took several years of concerted and collaborative effort between radiologists, clinicians, AI researchers and software engineers. In this talk I give an overview of the large-scale effort initiated by IBM Research to produce such a fully automated preliminary read capability covering a comprehensive list of findings that match or exceed the performance of entry-level radiologists. The work involved making simultaneous advancements in many fields of AI ranging from design of neural networks, text analytics, etc. to building clinical knowledge and reasoning systems and conducting various clinical studies to qualitatively and quantitatively assess the performance of AI systems in healthcare.
Short Biography: Dr. Tanveer Syeda-Mahmood is an IBM Fellow and global leader for imaging AI in IBM Research. Over the last decade she was involved in pioneering the field of radiology AI decision support through a large-scale research effort as the Chief Scientist of the Medical Sieve Radiology Grand Challenge. She also shepherded the transition of the underlying technologies to define the new products from Watson Health called Patient Synopsis and Clinical Review. Over the years, Dr. Syeda-Mahmood has led the transformation in many related AI fields including being the originator of the field of content-based retrieval in multimedia. Dr. Syeda-Mahmood has over 200 refereed publications and over 100 issued patents. She has led the organization of many conferences over the years including CVPR 2008 (Program co-Chair), IEEE HISB-2011 (General Chair), IEEE ISBI 2022 (Program co-Chair), and MICCAI 2023 (General Chair). Dr. Syeda-Mahmood is a Fellow of IEEE, and an AIMBE Fellow.