Dr Mike Allen
Senior Research Fellow in Applied Healthcare Modelling and Data Science
Expertise
Modelling, Data Science, Machine Learning
Biography
My main interests are the application of modelling and machine learning to understanding and improving clinical pathways. Work, for example, includes modelling of the acute stroke pathway, with machine learning being used to understand and predict clinical decision making, allowing us to ask questions such as “what treatment would this patient receive if they went to another hospital?”.
I also have a general interest in how ‘deep reinforcement learning’ may be applied to healthcare. Can, for example, the Deep Mind agents that learned to play Go and Chess learn how to manage escalation/de-escalation policies in a hospital?
Publications
- What would other emergency stroke teams do? Using explainable machine learning to understand variation in thrombolysis practice
- What would other emergency stroke teams do? Using explainable machine learning to understand variation in thrombolysis practice
- National implementation of reperfusion for acute ischaemic stroke in England: How should services be configured? A modelling study
- Use of Clinical Pathway Simulation and Machine Learning to Identify Key Levers for Maximizing the Benefit of Intravenous Thrombolysis in Acute Stroke
- Mechanical thrombectomy for acute ischaemic stroke: an implementation guide for the UK – Second edition February 2022
- Avoidable Acute Admissions
- A simulation modelling toolkit for organising outpatient dialysis services during the COVID-19 pandemic
- How can consultant-led childbirth care at time of delivery be maximised? A modelling study
- Exploring the cost-effectiveness of mechanical thrombectomy beyond six hours following advanced imaging in the UK
- Can clinical audits be enhanced by pathway simulation and machine learning? An example from the acute stroke pathway.
- Mechanical thrombectomy for acute ischaemic stroke: an implementation guide for the UK – First edition August 2019
- Planning and providing acute stroke care in England: the effect of planning footprint size
- Maximising access to thrombectomy services for stroke in England: A modelling study
- Feasibility of a hyper-acute stroke unit model of care across England: a modelling analysis
- A framework to accelerate simulation studies of hyperacute stroke systems
- How can frontline expertise and new models of care best contribute to safely reducing avoidable acute admissions? A mixed-methods study of four acute hospitals.
- Right cot, right place, right time: improving the design and organisation of neonatal care networks
- Involving patients and the public in healthcare operational research
- Involving patients and the public in healthcare operational research – the challenges and opportunities
- Providing one-to-one care in labour. Analysis of ‘Birthrate Plus’ labour ward staffing in real and simulated labour ward environments
Other team members
Jemma Phillips
Research and Communications Administrator
Sammi Rosser
Postdoctoral Research Fellow
Andy Mayne
PenCHORD Honorary Associate Research Fellow
Amy Heather
Postdoctoral Research Associate
Dr Anna Laws
Research Associate
Dr Thomas Monks
Associate Professor of Health Data Science
Chrissie Walker
PenCHORD Research and Operations Manager
Kerry Pearn
Research Fellow
Professor Martin Pitt
Professor of Applied Healthcare Modelling and Data Science