Queen Mary University of London, in collaboration with Barts Health NHS Trust, London's Air Ambulance and the University of Aberdeen, has secured a £1.8 million ($2.27 million) contract to support a clinical trial using the Artificial Intelligence in Trauma Risk Prediction System (AI-TRiPS).
AI-TRiPS is an innovative, AI-powered decision-support tool designed to assist in time-critical medical decision-making for severely injured patients.
The study, one of the first randomised-controlled trials to evaluate the use of AI-powered decision-support tools in trauma care, will see AI-TRiPS deployed across The London Trauma System, the largest integrated trauma network in the world which serves over 10 million people. It will involve trauma specialists from London's four major trauma centres as well as doctors and paramedics from London's Air Ambulance and the London Ambulance Service.
Funded by the Congressionally Directed Medical Research Programs, researchers will evaluate and determine the effectiveness of AI-TRiPS in supporting doctors assess the risks of life-threatening complications, such as severe blood loss, and support them in taking action to improve outcomes. If successful, this initiative could revolutionise trauma care worldwide and help save thousands of lives.
AI-TRiPS represents a true collaboration between medical and engineering experts at Queen Mary University and across the globe. The AI algorithms, developed by trauma surgeons, military experts, and computer scientists, integrate cutting-edge trauma research, registry data, and clinical expertise. The system is designed to be user-friendly, providing clear and accessible insights to doctors making decisions about seriously injured patients. It offers evidence-based predictions about the risks faced by critically injured patients and guidance on how best to manage these on arrival in hospital. Importantly, the system explains the reasoning behind its predictions, ensuring transparency with an "open box" design that can be easily understood and explored by clinical users.
"This is a pioneering step forward in trauma care," said Colonel Nigel Tai, Honorary Professor of Trauma Surgery and Innovation at Queen Mary and lead investigator for the study. "It is very exciting to be part of a great team who've worked so hard over the past decade to bring this research from concept through to implementation.
"We think that victims of major trauma - civilian and military - stand to benefit from new technologies, designed to give clinical teams the right information about their patients when they needed most. However, this attractive notion - of improving care by equipping Emergency Departments with advanced, AI-powered decision support systems - is still an unproven assumption.
Our research, funded by this contract, will put these tools to the test, by harnessing the world-leading London Trauma System and using a rigorous randomised trial protocol.
"The AI-powered tools we want to evaluate have been co-designed by trauma clinicians, working hand-in-glove with computer scientists. Whilst many AI applications have been developed, few are trialled, meaning that doctors and patients can't make good judgements about safety and efficacy, and developers lack feedback."
Dr William Marsh, Technical Lead and Senior Lecturer in Computer Science at Queen Mary, highlighted the significance of the interdisciplinary collaboration: "This project exemplifies the power of bringing together engineering innovation and clinical expertise to tackle urgent real-world problems."
Professor Karim Brohi, Director of the London Trauma System and Professor of Trauma Sciences at Queen Mary, stated: "London has always been at the forefront of trauma innovation. This study could push the boundaries further, potentially transforming how we deliver care and save lives globally."
The trial is part of a broader ambition to introduce AI-powered decision-support tools in diverse settings, from civilian emergency care to military operations. The algorithms have been designed with adaptability in mind, aiming for application in complex environments such as battlefield medicine.
The clinical trial, supported by the University of Aberdeen's Clinical Trials Unit, will begin with a year of development and regulatory approvals in January 2025. Patient recruitment will follow in early 2026, with results expected in 2027.
