Hosted by the School of Medicine at Cardiff University

2024 was the 'year of AI’ in many fields. Whilst undoubtedly application of transformer-based deep learning models to problems and their use in building Large language Models has provided a whole toolbox of assistance for human tasks, application of safe, reliable AI in medicine remains more challenging. This talk will cover recent work on building bespoke models using BERT and their potential for application in supporting primary care diagnosis via autonomous agents. A recent new NIHR i4i grant with SOAP Health, a US start up will be described.

Register via Eventbrite 

Professor Brendan Delaney is Chair in Medical Informatics and Decision Making at Imperial College London. He is an internationally leading exponent of the “Learning Health System" (LHS) concept. Although his initial training in research was in heath technology assessment, real-world (pragmatic) clinical trials and clinical research in Family Medicine, since 2003 Brendan has worked in the area of Clinical Informatics, being appointed to a Chair in Medical Informatics at Imperial in 2015 and elected one of the first 100 founding fellows of the new UK Faculty of Clinical Informatics in 2017 (Now Health and Social Care Faculty of the British Computer Society). At Imperial, he works in the Institute of Global Health Innovation, with research in Artificial Intelligence, cancer diagnosis and learning systems, eSource for clinical trials and global eHealth. His interests lie at the intersection of health services research (how to deal with patient problems equitably and efficiently), data semantics and clinical meaning, and machine learning based model validation and evaluation. Currently there are three areas of active research (1) Cancer diagnosis in Primary Care, (2) Computable Clinical Guidelines and Explainable AI, (3) Evidence-based management and learning from data in COVID-19.