Identifying people with MLTC in unscheduled care in the last year of life
Supervisors:
Prof Colin McCowan, Population and Behavioural Sciences Division, Medical School (University of St Andrews)
Prof Nazir Lone, Centre for Population Health Sciences, Usher Institute, University of Edinburgh
Dr Sarah Mills, Population and Behavioural Sciences Division, Medical School (University of St Andrews)
Dr Kirsty Boyd, Centre for Population Health Sciences, University of Edinburgh
Summary:
People with multimorbidity are often not identified as being near their end of life, and as such, are unaware of their limited prognosis and denied the opportunity to engage in future care planning. This project uses a machine learning approach to support clinical decision-making in unscheduled care, in order to improve the identification of people with multimorbidity who are in their last year of life.
The overall aim of the studentship is to develop and evaluate the performance of a new digital screening tool that identifies people who may benefit from future care planning in unscheduled care settings, and to compare this with existing tools. Proactive screening reduces inequity and enables more people with non-cancer illnesses, mixed physical/mental multimorbidity and socioeconomic deprivation to discuss their preferences and priorities for care with professionals.
The project will use unscheduled care datasets to develop and explore the performance of a new predictive tool to identify patients in the last year of life and to compare this against existing algorithms. Students will focus on external validation and improving the prediction models especially around for specific groups of patients of interest.
The studentship will provide training in epidemiology and statistics, data science, prediction modelling/machine learning.