Job Description

We are looking for a committed and enthusiastic post-doctoral statistician or data scientist with proven experience of applying state-of-the-art statistical and machine learning methods to healthcare data. The post holder will join the Critical Care Research Group (CCRG), led by Professor Peter Watkinson. The CCRG undertakes a programme of research that focuses on the early identification of patient deterioration and long-term outcomes of patients admitted to Intensive Care Units.
The post sits within the Oxford BRC "Digital Health from Hospital to Home" research theme, a long-standing, productive partnership between engineers, biomedical scientists and clinicians with an internationally recognised track record in delivering clinically validated and successfully commercialised digital technologies for patient benefit. The post holder will play an active role across components of the theme. We believe that integrating artificial intelligence (AI) algorithms and state-of-the-art monitoring will deliver early detection of not only unrecognised chronic conditions but also acute patient deterioration. Our vision is to deliver technology-enabled, patient-focused solutions from the intensive care unit (ICU) to the home, improving quality of care and breaking down boundaries between hospital, community, and the home.
The CCRG group specialises in analysing large datasets of routine healthcare data, providing knowledge both to underpin current clinical practice and from which to undertake large-scale randomised controlled trials, and in developing predictive models in critical illness.
Our multi-disciplinary team includes clinicians, nurses, physiotherapists, biomedical engineers, statisticians, and qualitative researchers. We have long-standing academic collaborations with machine learning experts (Professors Lionel Tarassenko & David Clifton, Institute of Biomedical Engineering), medical statisticians (Professor Gary Collins & Dr Stephen Gerry, Centre for Statistics in Medicine), and the Intensive Care National Audit & Research Centre (ICNARC). Other collaborators include primary care clinicians (Andrew Farmer, Nuffield Department of Primary Care), obstetricians (Professor Marian Knight, Nuffield Department of Population Health) and cardiologists/cardiac anaesthetists (Professors Gregory Lip at Liverpool Heart and Chest Hospital and Ben O'Brien Charite Universitatsmedizin Berlin).
Our core aim is to translate advances in biomedical technology, statistics and machine learning into clinical tools to improve outcomes for critically ill patients. Examples of previous impact include:

• Being the first in the world to demonstrate noncontact monitoring of oxygen saturations in clinical environments using webcams
• Developing and implementing an evidence-based early warning score system (SEND) in multiple NHS hospitals

Over the past five years, the group has received over 12 million in external funding from the NIHR, Wellcome Trust and Department of Health. Our group regularly publish in high-impact medical journals, such as the BMJ, Lancet, Nature Medicine, and Intensive Care Medicine.
Reporting to Professor Watkinson, you will make key contributions to our research programme by applying your previous experience of state-of-the-art statistical and machine learning methods to healthcare data. Working closely with senior statisticians, machine learning experts and clinicians, you will design and implement analysis of large patient cohorts, from data extraction to statistical analyses. You will lead and contribute to peer-reviewed publications and funding applications.
This post is full time and fixed term for 2 years in the first instance with the possibility of extension.
Only applications received before midday 12:00 on Friday 7th November 2025 will be considered.
Interviews will be held as soon as possible thereafter.
Contact Person: NDCN HR Recruitment
Closing Date & Time: 07-Nov-2025 12:00
Pay Scale: STANDARD GRADE 7
Contact Email:
Click on the link(s) below to view documents:
39,424 to 47,779 per annum

Skills Required