BloodCounts! Consortium wins Trinity Challenge Prize for breakthrough in infectious disease detection
BloodCounts! is an international consortium of scientists led by Professor Carola-Bibiane Schönlieb from the University of Cambridge Department of Applied Mathematics and Theoretical Physics and including Dr Nicholas Gleadall from the Department of Haematology and NHS Blood and Transplant. It has been awarded a substantial prize by the Trinity Challenge to further develop their innovative infectious disease outbreak detection system.
The Trinity Challenge is a global call for solutions that use data and analytics to tackle infectious disease outbreaks. It was launched in response to the COVID-19 pandemic, which highlighted the need for simple, affordable, and scalable technologies for the early detection of novel emerging disease outbreaks.
Much of the development of BloodCounts! solution was carried out by Dr Gleadall and Dr Michael Roberts from the University of Cambridge Department of Applied Mathematics and Theoretical Physics. It uses data from routine blood tests and powerful AI-based techniques to provide a ‘Tsunami-like’ early warning system for novel disease outbreaks.
Dr Roberts says “Since the beginning of the pandemic I have been developing AI-based methods to aid in medical decision making for COVID-19 patients, starting with analysis of chest X-ray data. Echoing the observations made by the clinical teams, we saw profound and unique differences in the medical measurements of infected individuals, particularly in their full blood count data. It is these changes that we can train models to detect at scale.”
Dr Gleadall says “We realised that hundreds of millions of full blood count tests were being performed every day worldwide, and this meant that we could apply our AI-methods at population scale. Usually the rich measurement data are discarded after summary results have been reported, but by working with Cambridge University -, Barts Health London -, and University College London – NHS Hospitals, we have rescued throughout the pandemic the rich data from 2.8 million full blood count tests.”
Importantly, unlike many other detection methods, BloodCounts! requires no prior knowledge of a specific pathogen but scans the full blood count for signs of pathogen detection by the human immune system. The full blood count is the world’s most common medical laboratory test, with over 3.6 billion being performed worldwide each year. This means that the BloodCounts! team can rapidly apply their methods to scan for abnormal changes in the blood cells of large populations by observing changes in the blood measurements associated with infection and then alert public health agencies to potential outbreaks of pathogen infection.
BloodCounts! has been supported by Professor Bryan Williams, Director of the NIHR University College London Hospitals Biomedical Research Centre, who was an early supporter of applying AI to the full blood count data. He says “The BloodCounts! approach has huge potential and if this works, it could provide a readily scalable and cheap population surveillance method for outbreak detection of SARS-CoV-2 and other viruses. A major advantage is that the NHS already performs more than 100 million FBC tests every year, with over half of these performed by general practitioners in the community, so the programme aims to get more information from tests we already perform.”
BloodCounts! is a unique solution giving a powerful demonstration of how the application of AI-based methods, built upon rigorous mathematics, can lead to huge healthcare benefits when applied in many areas of medicine.