Clinical outcome modelling
Self-funded PhD students only
School of Computing, Centre for Healthcare Modelling and Informatics
Applications accepted all year round
The work on this project will aim to:
- develop a new mortality prediction tool that can be used to identify changes in a hospital’s clinical outcomes and to compare the performance of hospitals
- build on our unique dataset of vital signs data and laboratory results, coupled with information drawn from other clinical information systems
The Centre for Healthcare Modelling and Informatics (CHMI) is a long-established health informatics research and innovation group. In collaboration with Portsmouth Hospitals and others, our work in clinical outcome modelling has supported the development of the VitalPAC vital signs collection system and the National Early Warning Score (NEWS) recommended by the Royal College of Physicians, among many other projects.
The aim of the project is to develop a new mortality prediction tool that can be used to identify changes in a hospital’s clinical outcomes and to compare the performance of hospitals. The expected mortality is based on the number of patients and the seriousness of their condition (obviously, very sick people are more likely to die than those who are not). A hospital where significantly more patients die than expected could be underperforming.
Current tools used for this (e.g. HSMR and SHMI) are based on the administrative data that records the diagnoses associated with a patient's hospital stay. They adjust for various factors such as the patient's age, sex and their existing medical problems.
However, the data can be "gamed" and the quality of the data is variable – for example, it is often recorded long after the patient has left the hospital and only analysed much later.
This project would start from the position that clinical performance should be measured by clinical data. Actual data, recorded as part of the normal delivery of care (such as the results of laboratory tests on blood and vital signs taken at the start of a patient's stay) are less prone to error or gaming, and should provide an objective (physiological) ruler with which to measure a patient's degree of sickness.
More and more of this sort of data is now available in NHS hospitals. Several aspects of the problem are open to investigation including how the tool could be calibrated initially and adjusted according to changing practice.
This project will build on our unique dataset of vital signs data and laboratory results, coupled with information drawn from other clinical information systems. Data from a second hospital may be available for comparison purposes.
A student undertaking this work could expect to find employment in healthcare data analytics (either in the NHS or in industry) or health service management, as well as in academia.
- You'll need a good first degree from an internationally recognised university (minimum upper second class or equivalent, depending on your chosen course) or a Master’s degree in an appropriate subject.
- In exceptional cases, we may consider equivalent professional experience and/or Qualifications.
- English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.
How to apply
Please contact Professor Jim Briggs (firstname.lastname@example.org) to discuss your interest before you apply, quoting the project code CCTS4570219. When you are ready to apply, you can use our online application form and select ‘Computing’ as the subject area. Please note: to be considered for this self-funded PhD opportunity you must quote the project code when applying.
Please ensure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV.
Our ‘How to Apply’ page offers further guidance on the PhD application process.