Routine clinical practice generates a large amount of data that is under-used for research and quality improvement. This is particularly true in paediatric intensive care units (PICU) across the world. Every PICU patient routinely has multi-parameter bedside physiological monitoring data in at least minute-by-minute resolution collected throughout their PICU stay. 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 outcome. Lack of linkage to other data sources collected during routine clinical care (e.g., radiological images, outcome such as re-admission following index PICU admission) prevents meaningful use of this physiology data to advance patient care and safety. We urgently need to utilise data science research and innovation to integrate the massive amount of data generated from different sources during routine patient care and develop precision medical approaches for critical care to deliver continuously improved patient care and outcome.
The usefulness of a data intensive informatics approach to advance life-threatening traumatic brain injury (TBI) intensive care management is demonstrated by our BrainIT and GBINARy groups and the KidsBrainIT initiative in adults and children, respectively. Applying data science research to ‘big data’ generated through ICU care of TBI patients of all ages in multiple ICU across different countries, our research consortium has successfully defined clinical and physiological phenotypes associated with an improved global neurological outcome[2,3]. We now need to better understand the impact of physiological phenotypes on structural and functional outcome in critically brain injured paediatric patients in order to improve their quality of life.
Radiological imaging modalities (e.g., CT, MRI) used in the clinical management of life-threatening TBI allow detection of structural abnormalities offering prognostic information and structural outcome assessment. Unplanned re-admission or emergency service presentation following PICU discharge is a proxy measure of poorer quality of life. Linking ICU clinical and physiological data with routine radiological images, unplanned hospital re-admission, or emergency service presentation from the community offer a valuable opportunity to better understand changes to the brain’s structure, functional ability, and quality of life following TBI at an individual patient level, leading the way for not only significant advances in understanding of TBI but also opening up the possibility to apply machine learning algorithms to predict hospital re-admission and emergency service re-presentation from data available at discharge. This would lead to personalised therapeutic strategies. Furthermore, this linkage informatics and machine learning approach for research in critically brain-injured patients may be extended to include all patients in ICU regardless of disease and age and warrants investigation.
This collaborative project aims to test hypotheses on how clinical, physiological and radiological (structural) phenotypes in paediatric patients with life-threatening brain trauma affect the brain’s ability to auto-regulate blood flow and outcome (including functional screening, unplanned re-admissions, etc.) We additionally aim to use this as a stepping-stone to expand the application of data driven linkage informatics and machine learning to research beyond brain trauma within the critical care setting.
We provide a unique opportunity for the student to apply their developing quantitative and interdisciplinary skills to a variety of data types and sources. Specifically:
Understanding of the data collection environment in intensive care units.
Experience with ‘big data’, including data linkage technologies and platforms.
Supervised machine learning algorithms.
Analysis of physiological time-series routinely collected at clinical bedside.
Domain Knowledge in paediatric critical care pathophysiology including those with TBI (clinical / physiological ‘phenotypes’).
Development of personalised precision medicine 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. http://www.ed.ac.uk/studying/postgraduate/degrees/index.php?r=site/view&id=919
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: http://www.ed.ac.uk/usher/precision-medicine
Celi LA, Mark RG, Stone DJ, Montgomery RA. “Big data” in the intensive care unit. Closing the data loop. Am J Respir Crit Care Med 2013. 187(11): 1157-1160.
Güiza F, Meyfroidt G, Lo TYM, Jones PA, et al. Continuous optimal CPP based on minute-by- minute monitoring data: a study on a pediatric population. Acta Neurochir 2016. 122: 187-191.
Guiza F, Depreitere B, Piper I et al. Visualizing the pressure and time burden of intracranial hypertension in adult and paediatric traumatic brain injury. Intensive Care Medicine 2015. 41(6): 1067-1076.
Donaghy E, Salisbury L, Lone N, Lee R et al. Unplanned early hospital readmission among critical care survivors: a mixed methods study of patients and carers. BMJ Quality & Safety 2018. (http://dx.doi.org/10.1136/bmjqs-2017-007513)