• Being run by Barking, Havering and Redbridge University Hospitals NHS Trust, in partnership with the The Alan Turing Institute, the University of Warwick and the University College London Institute of Digital Health.
  • Will explore how best to assist the triage process by using advanced health analytics to quickly and effectively identify high-risk patients in emergency departments.
  • Exploiting a probabilistic early warning system (PEWS) based on machine learning/Artificial Intelligence technologies to promptly identify high-risk patients needing urgent care.
  • Will run from September 2018 to October 2019.

Hospital emergency departments are high-pressure environments where, due to time constraints and patient variability, there is high clinical uncertainty. Health care staff screen enormous numbers of potential patients daily in order to assess illness severity and identify high-risk patients needing urgent care.

The goal of this project from Barking, Havering and Redbridge University Hospitals NHS Trust is to assist this critical triage process by using advanced health analytics to quickly and effectively identify high-risk patients in emergency departments.

The Trust’s health analysis team has already developed a dashboard that displays patient-flow data in real-time. The next ambitious step is to augment this analytical tool with patient-specific data that can guide the decisions of managers and clinical staff as soon as people arrive at triage. This is an NHS-academic collaboration that was pioneered in September 2017 with the Healthcare Data Study Group Workshop hosted by the Alan Turing Institute.

Data will be drawn from around one million medical records obtained during triage at the emergency department at the Queen's Hospital in Essex over the last five years, as well as other electronic health records held within the hospital. These data will be used in a bespoke probabilistic early warning system (PEWS) tool to predict patient outcomes by generating personalised risk scores for subgroups that exhibit distinct risk profiles.

Implementation of the PEWS has the potential to improve the efficiency and safety of triage by reducing uncertainty, facilitating early life-saving interventions and reducing the risk of long waiting times for patients needing urgent care. The results of this project will be made portable and open so the concept will be easily transferable to other emergency departments nationwide.  

Contact information

For more information about this project, please contact Nik Haliasos, Digital Transformation Lead and Consultant Neurosurgeon, Barking, Havering and Redbridge University Hospitals NHS Trust.

You might also like...

News

New Artificial Intelligence projects funded to tackle health inequalities

News

NHSX’ NHS AI Lab and the Health Foundation have today awarded £1.4 million to four projects to...

Press release

Research reveals devastating and lasting impact of the pandemic on those asked to shield

Press release

Health Foundation statement on Networked Data Lab research surrounding clinically extremely...

Briefing

Assessing the impact of COVID-19 on the clinically extremely vulnerable population

Briefing

We present analysis from the Networked Data Lab on the impact the pandemic has had on the clinically...

Kjell-bubble-diagramArtboard 101 copy

Get social

Our #REALCentre analysis shows that to meet demand and recover from the pandemic, over the next decade the NHS work… https://t.co/YcGMwZKnAw

Follow us on Twitter
Kjell-bubble-diagramArtboard 101

Work with us

We look for talented and passionate individuals as everyone at the Health Foundation has an important role to play.

View current vacancies
Artboard 101 copy 2

The Q community

Q is an initiative connecting people with improvement expertise across the UK.

Find out more