Generative AI in Healthcare
Description
This volume brings together cutting-edge research at the intersection of artificial intelligence, clinical care, and public health. While it highlights the impact of generative AI, including large language models, it also delves into broader challenges such as fairness, robustness, scalability, and explainability.
Chapters explore:
-
Applications of Generative AI in healthcare and medicine
-
Strategies to reduce bias and improve equity in clinical AI
-
Tools for making model predictions more explainable and accountable
-
Approaches for real-world deployment at scale
-
Human-centered and governance frameworks for responsible AI
Rather than focusing on isolated use cases or technical performance alone, this book offers a systems-level perspective, bridging computational innovation with clinical and ethical relevance.
Designed for researchers, healthcare professionals, and innovators, this collection provides critical insights for anyone aiming to responsibly develop or implement AI in health contexts.
More details
Persons
Dr. Arash Shaban-Nejad is a leading expert in population and precision health informatics. He is currently an Associate Professor and Director of Population and Precision Health at the UTHSC-Oak Ridge National Laboratory Center for Biomedical Informatics, Department of Pediatrics, University of Tennessee Health Science Center. Dr. Shaban-Nejad received his PhD and MSc in Computer Science from Concordia University, Canada, and an MPH from UC Berkeley, along with post-doctoral training at McGill University and additional training at Harvard School of Public Health. His interdisciplinary research focuses on health AI, explainable AI, large language models, predictive modeling, epidemiologic surveillance, and causal reasoning. He has published extensively, and his research has been funded by several federal, state, and international funding agencies. Dr. Shaban-Nejad is a founding chair of the AAAI International Workshop on Health Intelligence and the lead editor of multiple book volumes on the applications of AI in healthcare and medicine.
Dr. Martin Michalowski is a Foundation Research Professor in the School of Nursing at the University of Minnesota, where he co-directs the Center for Nursing Informatics and the Digital Health Lab. With a PhD in Computer Science from the University of Southern California, he applies advanced AI techniques, ranging from heuristic planning to large language models, in nursing informatics and personalized medicine. He co-leads the Nursing and AI Leadership Collaborative and the Mobile Emergency Triage (MET) research group, and has been recognized as a Fellow of the American Medical Informatics Association and the International Academy of Health Sciences Informatics. With more than 100 publications and as a founding chair of the International Workshop on Health Intelligence and co-chair of the AIME society, Dr. Michalowski has helped shape global dialogue on digital health innovation. His work is funded by NIH, NSF, DARPA, and DoD, and has led to award-winning papers and startup ventures.
Dr. Simone Bianco is Vice President of Computation at Altos Labs, Bay Area Institute of Science, where he leads interdisciplinary research bridging biology, computational science, and regenerative medicine. Previously, he led synthetic biology and vaccine discovery efforts at IBM Research Almaden, contributing to multiple patents in systems biology and AI. Trained as a physicist, Dr. Bianco earned his degree from the University of Pisa and his PhD from the University of North Texas. His academic journey includes faculty positions at the College of William and Mary and UCSF, and he is a founding PI of the NSF Center for Cellular Construction. A TED speaker with over one million views, he actively promotes inclusive education and serves on the board of the PINC program at San Francisco State University. Dr. Bianco is also a co-chair of the AAAI International Workshop on Health Intelligence.
Content
1. Robustness, Equity, Scalability, and the Challenge of Explainability in the Use of Foundation Models in Medicine.- 2. Uncertainty Quantification of Deep Learning Models for Audio-driven Disease Diagnosis.- 3. Swin fMRI Transformer Predicts Early Neurodevelopmental Outcomes from Neonatal fMRI.- 4. Probabilistic Forecasting of U.S. County-Level Suicide Mortality Rates (2005-2020): Assessing the Impact of Social Determinants of Health.- 5. AI-SAM: Automatic and Interactive Segment Anything Model.