Project identifier: SDE_TVS_PROJ_206
Project title: Predicting antibiotic resistance to improve treatment of patients with sepsis
Lay summary: Antibiotics are key part of treating infections. However, use and over-use of antibiotics leads to bacteria developing antibiotic resistance, where antibiotics no longer work as expected. When antibiotics are given to patients with infections, doctors and other professionals try to balance giving treatments that have the best possible chance of working while also avoiding over-treating patients.
There are several key decisions when it comes to using antibiotics including which antibiotics to start, when to switch antibiotics, and when to stop.
We aim to use artificial intelligence approaches together with the information that is routinely collected when patients come to hospital to develop tools to predict the best antibiotic to start, when to switch and when to stop. We will compare the performance of the tools to decisions that hospital clinicians make. We will also compare the predictions made on which antibiotics to start to the results of laboratory tests looking for antibiotic resistance that are available later.
Public benefit statement: Ultimately, we are aiming to develop tools that will help care for patients and supporting giving them the best possible antibiotic treatment for infections. This could reduce deaths from antibiotic resistance, shorten the time patients spend in hospital and reduce the need for repeat hospital admission. Models could also assist healthcare workers prescribing antibiotics and reduce risks faced by healthcare organisations that may arise from patients not being prescribed effective antibiotics.
Organisation: University of Oxford
Date of signed agreement: 21/5/26
Health Research Classification System (HRCS) category: Infection
Current project status: Live – Data in Use
Multiple-SDE project: No
Lead SDE: TVS SDE
Participating SDEs/organisations: TVS SDE
Further reading: