About this event
This seminar will present the opportunities which exist when applying machine learning methods to physiological data. Computer systems deployed in hospital environments, routinely collect a large volume of data that can hold very useful information. However, the vast majority are either not stored and lost forever or are stored in digital archives and rarely re-examined. In recent years, there has been extensive work carried out by researchers utilising machine learning (ML) techniques on these data streams, to predict and prevent disease states. Such work aims to improve patient outcomes, to decrease mortality rates and decrease hospital stays and more generally, to decrease healthcare costs.
Work on improving lung protective ventilation, using ML methodologies for clinical decision support will be presented. Furthermore current data streams and research plans will be discussed, and look to the future, reporting on how physiological data holds clinically important information to aid in decision support in the wider hospital environment.
About the speakers
Rachael Hagan is a Research Fellow and PhD candidate at Queen’s University, Belfast (QUB). She holds a First Class Honors degree in Computer Science and has experience working as a Product Developer at Kofax Ltd. Her PhD research focuses on the application of machine learning methods to ICU data for predictive analytics, with various publications, in order to enhance patient care and clinical outcomes.
By completing a multidisciplinary PhD, Hagan has extensive understanding of the implementation of scientific methodologies for real world clinical problems.
Dr Charles J. Gillan (CG) is Senior Lecturer in the School of Electrical and Electronic Engineering and Computer Science at QUB. Before joining QUB in 2004, he was a visiting fellow at the Centre for Astrophysics at Harvard University before working on the ARCHEM toolset for computational chemistry at the IBM San José research laboratory. He then worked at ADP Inc., developing low latency multithreaded software handling market data for sovereign debt instruments and foreign exchange rates.
On returning to the UK in 1998 he was manager of a global software development team for data communication equipment at Nortel Networks (UK) Ltd. He has published over fifty papers. He coordinated the FP7 HANDHOLD (284456) project and was a Co-I on the FP7 NanoStreams (610509) project, the H2020 AllScale (671603) and UniServer (688540) projects. He held one InnovateUK KTP project (10692) with Foods Connected Ltd (2017–19) and is presently academic lead on another KTP (12982) with Bia Analytical Ltd (2021–23). He is a Co-I on Kelvin-2(EP/T022175/1).
Dr Murali Shyamsundar is a NIHR clinician Scientist Fellow/Consultant in Intensive Care Medicine Royal Victoria Hospital Belfast and Consultant Senior Lecturer, Queen’s University Belfast. His research programme includes development of novel pharmacotherapies to prevent and treat pulmonary injury and development of clinical decision support to improve translation of evidence to practice.