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.

HAVEN one vision, three funders, five NHS Foundation Trusts.

HAVEN is a collaborative multi-centre project to design and develop an advanced electronic early warning score to better identify patients who may need treatment on the intensive care unit. The project was funded by the Health Innovation Challenge Fund, a joint venture supported by the Wellcome Trust and the Department of Health. Since 2014 the University of Oxford, the University of Portsmouth, Portsmouth Hospitals University NHS Trust, and Oxford University Hospitals NHS Foundation Trust  have worked to develop an advanced electronic early warning score. Since 2020 the collaboration has expanded to include Royal Berkshire NHS Foundation TrustLancashire Teaching Hospitals NHS Foundation Trust and South Warwickshire NHS Foundation Trust

Project summary

Late recognition of deteriorating patients in hospitals causes treatment delays that result in increased mortality and morbidity. Despite widespread introduction of vital sign-based “early warning scores” deterioration of patients frequently goes unrecognised. Consequently, developing systems for early recognition of patients at risk of severe reversible deterioration has become a key goal for the NHS.

The HAVEN Project is developing a hospital-wide IT system that enables a continuous risk assessment in all hospital patients and predicts those at risk of deterioration. The IT system uses routinely stored electronic data (including demographics, laboratory results and vital signs recordings) to create a continuous risk assessment. At present, these different types of data are stored in different local databases and are not integrated or displayed in a way that supports decision making or calculation of patient risk. The project will implement a system to gather the relevant data so that it can be used to gauge risk.

Risk prediction algorithms have been developed and validated. They will use the records of patients who were admitted to hospital and then admitted to an intensive care unit (ICU) after two or more days in hospital. The information about these patients illustrates the pathway from the first signs of deterioration on the ward to ICU admission.

A prototype has been developed which will allow clinical staff to identify, rank, review and treat patients who, without acute medical intervention, will deteriorate and require ICU admission. The prototype was developed using Human Factors methods to determine the best way to present the information to support decision making.

This project has potential to increase ICU bed capacity and save money by reducing the number of patients admitted from the ward because their deterioration was recognised at an early stage.


Detecting Deteriorating Patients in Hospital: Development and Validation of a Novel Scoring System Published 2021

Cross-sectional centiles of blood pressure by age and sex: a four-hospital database retrospective observational analysis, published May 2020 

Frailty and unplanned admissions to the intensive care unit: a retrospective cohort study in the UK, published April 2020 

Deep Interpretable Early Warning System for the Detection of Clinical Deterioration, published February 2020 

Early warning score adjusted for age to predict the composite outcome of mortality, cardiac arrest or unplanned intensive care unit admission using observational vital-sign data: a multicentre development and validation, published November 2019 

Trajectories of vital signs in patients with COVID-19 published September 2020

Detecting Deteriorating Patients in Hospital: Development and Validation of a Novel Scoring System 

Implementing a system for the real-time risk assessment of patients considered for intensive care 

Testing a digital system that ranks the risk of unplanned intensive care unit admission in all ward patients: protocol for a prospective observational cohort study 

Patient centred variables with univariate associations with unplanned ICU admission: a systematic review 

How human factors affect escalation of care: a protocol for a qualitative evidence synthesis of studies

The effect of fractional inspired oxygen concentration on early warning score performance: A database analysis 

A comparison of the ability of the National Early Warning Score and the National Early Warning Score 2 to identify patients at risk of in-hospital mortality: A multi-centre database study 

Predicting in-hospital mortality and unanticipated admissions to the intensive care unit using routinely collected blood tests and vital signs: Development and validation of a multivariable model 

Usability evaluation methods employed to assess information visualisations of electronically stored patient data for clinical use: a protocol for a systematic review

Variables associated with unplanned general adult ICU admission in hospitalised patients: protocol for a systematic review 

The HAVEN project was presented at the Intensive Care Society State of the Art conference, December 2017. The posters presented can be seen online:

Decision making in the context of ‘big data’: Using the Delphi process to spot the needle in the haystack

Identification of barriers and facilitators to information exchange about a deteriorating patient’s escalation of care: A Human Factors Analysis

HAVEN Project Updates 

2020 HRA and CAG approval given to use data from Royal Berkshire NHS Foundation Trust, Lancashire Teaching Hospitals NHS Foundation Trust and South Warwickshire NHS Foundation Trust in the HAVEN algorithm.

October 2019: The HAVEN project has formally closed, and the final presentations were delivered to representatives from the funding body on 23rd October. The team is now concentrating on submitting publications from the last stages of the project.

June 2018: The Human Factors team have completed the first phase of user-testing the prototype interface. This interface has been designed using information extracted from interviews with 'target' clinicians (those who will be using the system when deployed). 

December 2017: Milestone Three achieved and confirmed with funding body. We also had two poster abstracts accepted for the Intensive Care Society State of the Art conference which was held in Liverpool.

June 2017: The whole research team met for a “Show and Tell” session in Portsmouth to present progress to date.  Presentations included an evaluation of early warning scores, an early example for the HAVEN scoring model that combined laboratory tests with vital signs with good results, and a demonstration of the IT infrastructure that will run the HAVEN system.

December 2016: First stage Human Factors interviews completed at both Oxford and Portsmouth

October 2016: Full R&D approval confirmed for both Oxford University Hospitals NHS Foundation Trust and Portsmouth Hospitals NHS Trust 

September 2016: HRA Approval confirmed

August 2016: Milestone Two achieved and confirmed with funding body

June 2016: Research Ethics Committee (REC) approval confirmed (ref: 16/SC/0264)

May 2016: Submission for ethical approval

February 2016: Milestone One achieved and confirmed with funding body

August 2015: Confirmed project start

May 2014: Funding awarded (refs: HICF-R9-524 and WT-103703/Z/14/Z)

January 2014: Final funding application submitted to the Health Innovations Challenge Fund

Contact details for the HAVEN project

The HAVEN project is co-ordinated by Rachel Henning who is based at the Kadoorie Centre for Critical Care Research & Education in Oxford