We are a multi-disciplinary team of researchers and educators who sit at the intersection of biology, medicine, healthcare, data, computing and methods. In research our guiding aim is to improve human health through the application of technology to solve hard problems. In education we are equipping the next generation of scientists and health care professionals with the skills they need to advance the field and to transform healthcare.

The Division is home to 50 full time academic staff and a similar number of researchers. We have a lively community of PhD students from around the world.

We are recognised as 1st in the UK and 4th in the world for highest citation impact in Digital Health. We have made a strategic investment in translating health technology into the NHS through The Christabel Pankhurst Institute, we are integral to the delivery of the Manchester NIHR-funded Biomedical Research Centres, Applied Research Collaboratives and Patient Safety Research Collaborative to integrate novel digital interventions into the health system. All these partnerships have a strong commitment to data-intensive research and collectively inform our education. The Division played a key role in establishing the GM Care Record and the Greater Manchester SDE.

Research Areas

Research is in three broad areas: health informatics; computational biology and imaging sciences. We apply the methods of data science, artificial intelligence and machine learning across our research portfolio.

Clinical Prediction Modelling

The clinical prediction modelling group conducts world-leading methodological and applied research into prognostic/predictive modelling. Prediction models are crucial as healthcare systems aim to shift from treatment to prevention of disease.

Knowledge support tools

In primary care, particularly those embedded within electronic health records (EHRs) to assist clinicians in real time. These tools leverage routine health data and predictive modelling to prompt timely, relevant clinical actions, ensuring practicality and usability.

Digital epidemiology

A strong focus on using technology to improve the understanding and treatment of rheumatic and musculoskeletal diseases. We have a strong focus on citizen science and patient generated health data.

Multi-modal machine learning for integration of spatial omics and histopathology data

We have expertise in machine learning models that combine spatial omics with other modalities such as single-cell omics, histology images (H&E) and clinical covariates.

Bioinformatics methods for high-resolution omics data

We develop computational and statistical methodology for gene regulatory network inference from single-cell data, collaborating with experimental laboratories within a team science approach. We are also adapting methods from geographical information systems (GIS) and techniques from spatial statistics with a focus on developing computational pipelines, analytical tools, and methodological frameworks for single-cell and spatial omics.

GenAI and virtual reality for healthcare training. 

We have developed virtual reality to remotely train healthcare professionals in paediatric emergency tracheostomy skills.

Health Services Research

We use real-world, big data from electronic health records and health service administration to understand the NHS through the lenses of quality, equity, efficacy and safety, with impact on policy.

Digital Intervention Research

We research how digital technologies can be used to deliver interventions and ways to evaluate them effectively.

Personal sensing

We use smartphones and wearable devices to understand the rhythms and fluctuations in diseases to enable personalised, precision medicine.

Image Acquisition: Developing new ways of collecting and analysing images using MR and PET machines.

Medical Image Analysis on Large-scale Studies

Developing automatic techniques to reliably extract useful measurements from images enabling diagnosis of disease, monitoring of treatment or estimation of risk.

Models of Anatomy

Using image information to build statistical and physical models of anatomical structures (bones, heart, brain) to understand how they vary across individuals or respond to disease.

Image-based In Silico Trials

Developing new methodology, processes and tools for delivering in-silico trials of imaging systems and other medical devices and enabling the emerging field of In-silico Regulatory Science.

Head of Division

Prof John Ainsworth

Our researchers

View a list of researchers within the Division

Contact

Prof John Ainsworth
email: John.Ainsworth@manchester.ac.uk