I am excited to be a co-author on this insightful paper by first author, and star researcher, Laith Alzubaidi.
Published in PLOS ONE, this study explores ways to create more reliable AI models for clinical practice. One of the key limitations of AI models is their propensity to be “confidently incorrect.” This study sheds light on ways to better design and assess AI models, which is particularly relevant in a clinical context where mistakes can have serious repercussions for patients.
Dr. Laith Alzubaidi, a postdoctoral researcher at the Queensland University of Technology, is the first author of this groundbreaking research. With a master's in computer science from the University of Missouri and more than 40 refereed research papers, Dr. Alzubaidi is collaborating with researchers around the world to lead the way in creating more reliable AI models.
Stay up-to-date with the latest developments in AI and clinical practice by checking out this fascinating study.
https://jointbiomechanics.org/
linkedin links:
ARC Training Centre for Joint Biomechanics