Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

A major focus of our research is improving outcomes for patients whose condition deteriorates in hospital.

Late recognition and treatment of deterioration occurs in 5% of patients admitted to NHS hospital, resulting in avoidable harm, including death. Over 60,000 patients each year deteriorate unexpectedly on wards to the extent they need to be transferred to an intensive care unit (ICU). Our work focusses on developing novel patient monitoring systems and state-of-the-art machine learning algorithms to detect deterioration early, enabling prompt remedial treatment to improve patient outcomes.

We developed the System for Electronic Notes Documentation (SEND), a user-optimised digital system for charting vital-signs (e.g., breathing rate, pulse) observations. In collaboration with the Department of Engineering and Oxehealth, we developed and tested the Oxevision system that uses advanced computer vision for non-contact vital signs monitoring. We are applying similar techniques in the MOLLIE study to detect changes in skin perfusion seen in critical illness.

In the NIHR-funded FOBS project, we have combined statistical and economic modelling with time-and-motion studies to optimise vital signs monitoring frequency in hospital.

Supported by the Wellcome Trust, Department of Health and the NIHR Oxford Biomedical Research Centre, we developed the Hospital-Wide Alerting Via Electronic Noticeboard (HAVEN) system to provide reliable, early detection of deteriorating patients. HAVEN is an externally-validated, real-time, AI-driven, hospital-wide system, which correctly detecting twice as many deteriorating patients than other published systems, without increasing clinical staff workload.