Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Researchers in the Primary Care Epidemiology Group are joining two landmark projects to combine healthcare data and artificial intelligence to improve cancer diagnosis

Lung cancer highlighted in the body

The Department of Primary Care and Health Sciences recently announced that researchers in the Primary Care Epidemiology Group are joining two landmark projects to combine healthcare data and artificial intelligence to improve cancer diagnosis.

Led by Professor Julia Hippisley-Cox, the team will utilise the QResearch database of routinely collected electronic patient health records for studies on lung and oesophageal cancer diagnosis.

The two projects, announced today as part of a £13m investment from UKRI through their industrial strategy challenge fund, brings together different strengths from academia, charities, digital health and diagnostics companies.

Both projects are part-funded by Cancer Research UK.

DELTA, led by the University of Cambridge, will help to diagnose oesophageal cancer, which has increased 6-fold since the 1990s. Just 15% of people will survive for 5 years or more – often because it’s diagnosed too late.

Barrett’s oesophagus, a condition that can turn into cancer of the oesophagus, is more common in patients who suffer with heartburn. By using a new test for patients with heartburn, called the ‘Cytosponge’, the project aims to diagnose up to 50% of cases of oesophageal cancer earlier, leading to improvements in survival, quality of life and economic benefits for the NHS.

Professor Hippisley-Cox’s team are leading on the clinical epidemiology element of this research programme. The researchers will interrogate the QResearch database with the aim of developing a risk prediction algorithm that will be able to identify those individuals at highest risk of oesophageal cancer for further investigation.

DART (The Integration and Analysis of Data Using Artificial Intelligence to Improve Patient Outcomes with Thoracic Diseases), led by the University of Oxford, will accelerate lung cancer diagnosis, increasing the likelihood that treatment will be successful. See the full story on this announcement here.

Academics, NHS clinicians, the Roy Castle Lung Cancer Foundation and industrial partners (Roche Diagnostics, GE Healthcare, Optellum) will work with the NHS England Lung Health Checks programme to combine clinical, imaging and molecular data for the first time using artificial intelligence algorithms.

Professor Hippisley-Cox’s team will link to data from primary care to better assess risk in the general population to refine the right at-risk individuals to be selected for screening. It is hoped that this research will define a new set of standards for lung cancer screening to increase the number of lung cancers diagnosed at an earlier stage, when treatment is more likely to be successful. Find out more about this project here.

The QResearch database is one of the largest clinical research databases in Europe, covering 35 million patients from 1,500 GP practices throughout the UK. It includes longitudinal data collected over 25 years that is linked at an individual patient level to Hospital Episode Statistics (HES), mortality data and cancer registration (more details here), making it an extremely rich resource for cancer research.

Similar Stories

Unique Clinical Imaging Dataset Released for Artificial Intelligence Research to Accelerate Diagnosis of Prostate Cancer

The National Cancer Imaging Translational Accelerator (NCITA) in partnership with the ReIMAGINE Consortium have announced the release of a unique clinical imaging dataset from the Prostate MRI Imaging Study (PROMIS)).

Measured weight loss associates with an increased risk of a cancer diagnosis

Weight loss is a sign of undiagnosed cancer regardless of the interval over which it occurs.

Comparing polygenic risk scores for risk prediction in individuals

Substantial disagreement in individual risk prediction was found between different polygenic risk scores for breast cancer, hypertension and dementia using genotyping data from the UK Biobank.