Computer Aided Risk Score

In a nutshell: The Improvement Academy is working with the University of Bradford, Northern Lincolnshire and Goole NHS Foundation Trust and York Teaching Hospitals NHS Foundation Trust to develop, implement and evaluate the impact of a novel real-time computer-aided risk score to support clinical decision making.  

The Challenge

Around 5% of deaths in English hospitals would be  prevented if care was optimised. About 31% of those deaths have been  estimated to be from poor clinical monitoring, 29.7% from diagnostic errors and 21% from inadequate drug or fluid management. These data suggest that clinical teams are not always aware of the patient’s actual risk of dying but if they were this could enhance patient safety. With the exception of Intensive Care Unit (ICU) teams, most other clinical teams do not have a statistically calculated score that gives practitioners a warning of risk of deterioration or death and the opportunity to take timely action to prevent this. 

What we are doing about it

The University of Bradford and the Improvement Academy have been awarded funding from the Health Foundation to conduct a 2 year study aiming to develop, implement and evaluate the impact of a novel real-time computer-aided risk score (CARS) to support clinical decision making based on linked physiological and biomedical data.  We are working with Northern Lincolnshire and Goole NHS Foundation Trust and York Teaching Hospitals NHS Foundation Trust to embed the score into routine clinical practice.

Combining routine blood tests with National Early Warning Scores (NEWS) can provide a valid computer-aided risk score within 24 hours of admission. These data are routinely collected and clinically validated as part of the process of care.  This offers a paradigm shift in the potential to enhance and support near real-time clinical decision making and quality and safety of care because this moves us away from measuring past harm to focusing on how safe care is and anticipating potential harms.

The physiological data is obtained from NEWS which is based on a range of vital signs (e.g. respiration (breathing) rate, blood pressure, heart rate, temperature) and the biomedical data is obtained from routine blood tests (e.g. albumin levels (indicate how the liver is coping), haemoglobin (cells that carry oxygen around the body),  white cell count (which may indicate infection)).

Potential advantages to CARS;

  • the variables that underlie the CARS are clinically meaningful validated and routinely collected;
  • are available early in the patients admission to hospital;
  • have a high degree of quality assurance (blood tests results have national quality assurance, whilst electronic NEWS (eNEWS) are much more accurate than paper based EWS)

Patient Voice

The AHSN Improvement Academy is using an innovative method of capturing the 'voice of patients' in improving the safety of their healthcare. Read about the PRASE (Patient Reporting and Action for a Safe Environment) tool here.

Further Information

Preventable deaths due to problems in care in English acute hospitals: a retrospective case record review study

The nature of adverse events in hospitalized patients. Results of the Harvard Medical Practice Study II

Index Blood Tests and National Early Warning Scores within 24 Hours of Emergency Admission Can Predict the Risk of In-Hospital Mortality: A Model Development and Validation Study.

Standardising the assessment of acute illness severity in the NHS. Report of a working party.

Acutely ill patients in hospital: recognition of and response to acute illness in adults in hospital.

Which Is More Useful in Predicting Hospital Mortality - Dichotomised Blood Test Results or Actual Test Values? A Retrospective Study in Two Hospitals. 

Incidence and significance of errors in a patient ‘track and trigger’ system during an epidemic of legionnaires’ disease: retrospective casenote analysis.

Calculating early warning scores – classroom comparison of pen and paper and hand-held computer methods.

Improving accuracy and efficiency of early warning scores in acute care. 

Evidence of methodological bias in hospital standardized mortality ratios: retrospective database study of English hospitals.

The findings of the Mid-Staffordshire Inquiry do not uphold the use of Hospital Standardised Mortality Ratios as a screening test for "bad" hospitals.

What is the empirical evidence that hospitals with higher risk adjusted mortality rates provide poorer quality care? A systematic review of the literature

Developing and evaluating complex interventions: new guidance.  





Natalie Jackson


01274 383931