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 on 'Find out more' to see our Cookie statement.

VisensiaTM, an ‘early warning’ system which developed out of research in the Department of Engineering, is making a significant impact on mortality rates for hospital patients in high-risk groups.

An example of a Visensia screen © OBS Medical

Around 23,000 people in the UK suffer in-hospital cardiac arrests each year, and mortality rates can be as high as 85 per cent. In addition about 20,000 UK hospital patients each year undergo an unplanned transfer to intensive care; the mortality rate for these is reported as 50 per cent, compared with 35 per cent for patients admitted directly to the same units. In 2005, the National Confidential Enquiry into Patient Outcome and Death estimated that sub-optimal care on wards contributed to around one third of the deaths there.

Extensive evidence shows that patients experiencing an adverse event such as a cardiac arrest show abnormal physiology in the hours preceding the event. VisensiaTM is designed to detect these changes so that an early intervention can be made, which improves patient outcomes. The computer-based bedside system, pioneered by Professor Lionel Tarassenko and colleagues, is now deployed in hospitals in the UK and US. It automatically and continuously monitors hospital patients’ vital signs, produces simple-to-read scores, and alerts healthcare staff to any deterioration in a patient’s condition so that they can intervene quickly.

VisensiaTM was made possible by advances in novelty detection (algorithms which can detect patterns outside the boundaries of a model of normality). Working with Professor Stephen Roberts, Professor Tarassenko developed a new approach to novelty detection that enabled identification of epileptic seizures in recordings of electrical activity in the brain. With Professor Sir Michael Brady, Tarassenko then used similar algorithms first to ‘learn’ a description of normal breast tissue from mammograms, and then to identify possible tumours by testing for novelty against this description.

Funding from the EPSRC enabled Tarassenko to apply the new techniques to two very different fields: monitoring jet engine health, and monitoring hospital patients. In the second of these areas, novelty detection was applied to the five vital signs (heart rate, respiratory rate, oxygen saturation, blood pressure and temperature). A detailed model of normality was learnt from hundreds of hours of data collected from patients connected to bedside monitors, enabling development of a ‘patient status index’ that would indicate deviation from the norm.

The first clinical trial of VisensiaTM took place at Oxford’s John Radcliffe Hospital from 2003 to 2005. This was followed by a second trial in the US from 2006 to 2009, which showed that VisensiaTM could alert staff to serious patient deterioration more than six hours before they would normally call the crash team. It also led to a significant fall in the number of patients becoming critically unstable for a sustained period of time, and reduced unexpected fatal cardiac arrests on trial wards to zero. This conclusive evidence resulted in the system securing FDA approval in 2008.

The successful US trial has been pivotal to VisensiaTM’s commercial success. From 2008 to 2012, take-up of Visensia™ in UK and US hospitals generated total sales amounting to around £1.5 million for OBS Medical, the company licensed to develop a commercial product. Tarassenko’s research has led directly to a cut in mortality rates in the US and UK hospitals where Visensia™ is now deployed. Patients are key beneficiaries, but so too are healthcare staff whose jobs have been made easier and less stressful, since they can concentrate efforts on the highest-risk patients.

Research funded by the EPSRC and the NIHR Biomedical Research Centre Programme.

Image courtesy of OBS Medical.

Case studies