AI in action: predicting hospital outbreaks with statistical precision


A 3d rendering of the COVID virus

Dr Jess Bridgen and Professor Chris Jewell of the Department of Mathematics and Statistics have been working in collaboration with Lancaster Medical School’s Dr Jon Read and infectious disease doctors at the University of Liverpool to develop a ground-breaking new way of tracking and predicting outbreaks of infectious diseases within healthcare settings.

Outbreaks of infectious diseases such as COVID, MERS, and MRSA in hospitals have been adding a significant burden to not only the NHS, but healthcare systems around the world. Particularly during the recent COVID pandemic, incidences of healthcare-associated infections were very high, in spite of the infection control measures put in place. The biggest barrier to predicting and managing these infections is understanding how these are transmitted in the first place – for example, whether it is staff inadvertently transmitting diseases between wards, patients interacting with other infected patients, or hospital visitors bringing and transferring infections from outside within hospital grounds. Naturally, it is very difficult to monitor patients, staff and visitors for infection at all times, and although hospitals take note of when a patient first tests positive for an infection, the time they contracted that infection and when they cease being infectious is often unknown, making it difficult to pinpoint the source of that infection and the subsequent infections of other patients.

In order to tackle these uncertainties, Dr Bridgen and the team developed a cutting-edge Bayesian statistical approach to epidemic modelling. Using data gathered of staff and patient movements within and between wards and the typical infectious period of a disease, they were able to create a model capable of predicting at what point patients contracted the disease, therefore allowing the statisticians to see the most likely source of that infection. Although their model was produced and tested using COVID outbreaks within a UK hospital during the pandemic, the hope is that similar forms of AI will be able to map out potential infection hazard points for a multitude of infectious diseases, allowing hospital infection control teams to intervene earlier and ultimately preventing small introductions of disease such as flu, COVID, and anti-microbial resistance turning into uncontrollable hospital-acquired outbreaks.

On the exciting possibilities that this AI model has to offer, Professor Jewell remarked that “this project demonstrates the power of cutting-edge Bayesian analysis when coupled to real-world patient data. It gives us a method of seeing through a noisy, complex world to get to the heart of a very real infection control challenge that hospital staff face on a daily basis."

Dr Jess Bridgen also added: “As an early career researcher, this project was a great opportunity to apply novel statistical methodology to a real-world application. This research presents an avenue for further AI innovation in infection control to detect at-risk areas of hospitals and evaluate control interventions.”

Back to News