Coventry University Featured PhD Programmes
University College London Featured PhD Programmes
University of Glasgow Featured PhD Programmes
Imperial College London Featured PhD Programmes
University of Reading Featured PhD Programmes

Precision Medicine DTP - Developing data science approaches to improve paediatric critical care patient flows and its related health economics benefits in Scotland

Project Description


Paediatric critical care (PCC) is a highly valued specialist service that saves infants and children’s life. Over the past decade, the demand of PCC beds exceeds the expected population growth in the UK. Reasons for this progressively worsened PCC bed crisis include: seasonal peaks of respiratory viral infections; gradual change in PCC patient characteristics over the past decade with more complex patients having multi-morbidities; and delayed discharges from paediatric critical care units (PCCU). PCC bed crisis has impact on patient care, safety, and outcome as critically ill infants and children need to wait longer in non-specialist settings before receiving this subspecialty care.

In Scotland, paediatric critical care service is a national service delivered through two PCCU located in the children’s hospitals in Edinburgh and Glasgow respectively. Both children’s hospitals routinely collect quantitative bed occupancy and staffing data and their PCCU also routinely collect quantitative data on all patients referred for admissions including time of referral, and actual time of admission etc. Furthermore, every PCCU patient routinely has multi-parameter bedside physiological monitoring data in at least minute-by-minute resolution collected throughout their PICU stay. But yet once the patient is discharged, vital information from this physiological big data is discarded rather than being used to advance our understanding of how a patient’s physiological phenotype may affect their hospital journey from admission to discharge. There is now a unique opportunity to link routinely generated data from different souces and harness their power towards improving patient flow into PCCU in Scotland.

We know from the literature that applying data science techniques on real patient data can assess risks of delay in hospital admission and discharge pathway in adults [1]. We now urgently need to employ similar methodology to children’s in-hospital data linked from different sources if we want to improve patient flow into and out of PCCU in Scotland, and to enhance the health economics of our clinical practice.


This multi-disciplinary project aims to develop data science approaches to improve paediatric critical care patient flow in Scotland and to assess its potential health economical benefits. Our research objectives are to:

Model and analyse existing PCC patient flow with the use of process mining [2] and network analysis techniques to gain an insight into patterns of flow and variations based on patient characteristics.
Simulate different PCC scenarios with the use of workflow technologies and agent-based techniques [3] to identify bottlenecks and perform what-if analysis towards improvement.
Build a prediction model with the use of machine learning techniques [4] to predict the length of stay and care trajectory of individual patients according to their phenotypes, and ultimately help to plan their care including discharge progress.
Assess the health economic benefits of data-driven PCC patient flow improvment.
This project is a stepping stone to translate our novel approaches to benefit the wider paediatric critical care community in the UK.

Training Outcomes

We provide a unique opportunity for the student to apply their developed quantitative and interdisciplinary skills to a variety of data types and sources. Specifically:

Digital Excellence

Understanding of the data collection environment in critical care units, hospital management team etc.
Experience with ‘big data’ including data linkage technologies and platforms.

Machine learning algorithms
Medical informatics
Process mining and network analysis techniques
Workflow- and agent-based simulation methods
Health economics analyses
Time-series routinely collected clinical bedside physiological data analysis skills.

Domain Knowledge in paediatric critical care pathophysiology (clinical / physiological ‘phenotypes’).
Development of precision medicine approaches to improve patient flow for paediatric critical care.

This MRC programme is joint between the Universities of Edinburgh and Glasgow. You will be registered at the host institution of the primary supervisor detailed in your project selection.

All applications should be made via the University of Edinburgh, irrespective of project location. For those applying to a University of Glasgow project, your application along with any supporting documents will be shared with University of Glasgow.

Please note, you must apply to one of the projects and you must contact the primary supervisor prior to making your application. Additional information on the application process is available from the link above.

For more information about Precision Medicine visit:

Funding Notes

Start: September 2020

Qualifications criteria: Applicants applying for a MRC DTP in Precision Medicine studentship must have obtained, or will soon obtain, a first or upper-second class UK honours degree or equivalent non-UK qualification, in an appropriate science/technology area.
Residence criteria: The MRC DTP in Precision Medicine grant provides tuition fees and stipend of at least £15,009 (RCUK rate 2019/20) for UK and EU nationals that meet all required eligibility criteria.

Full eligibility details are available: View Website

Enquiries regarding programme:


1] Mathews K, Long E. A conceptual framework for improving critical care patient flow and bed use. Annuals of American Thoracic Society. 2015 Jun; 12(6): 886-94.

[2] Rojas E, Munoz-Gama J, Sepúlveda M, Capurro D. Process mining in healthcare: A literature review. Journal of Biomedical Informatics. 2016 Jun; 61:224-36.

[3] Isern D, Moreno A. A systematic literature review of agents applied in healthcare. Journal of Medical Systems. 2016 Feb; 40(2):43.

[4] Xu H, Wu W, Nemati S, Zha H. Patient flow prediction via discriminative learning of mutually-correcting processes. IEEE transactions on Knowledge and Data Engineering. 2016 Oct; 29(1):157-71.

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.