en.Wedoany.com Reported - Dr. Paul Young, Deputy Director of the Medical Research Institute of New Zealand and Joint Clinical Lead of the ICU at Wellington Hospital, has received a $5 million grant from the Health Research Council of New Zealand (HRC) to lead a major clinical trial called REVOLUTION. This trial will test whether artificial intelligence can help doctors improve survival rates for patients on life support in intensive care units across 50 hospitals in New Zealand and Australia.
This study, titled "Randomised Evaluation of Oxygen Thresholds Using Individualised Assessment," is the world's first trial to evaluate whether machine learning-guided AI treatment can improve ICU survival rates, and plans to recruit over 24,000 patients. Dr. Young stated that even if only a modest reduction in deaths is confirmed, the protocol could save hundreds of thousands of lives annually in ICUs worldwide.
A statement from the Health Research Council (HRC) noted that if successful, the trial could set an international benchmark for the safe and rigorous application of AI-derived models in clinical decision-making. This grant is one of two programme grants announced by the HRC, totaling $10 million, and also includes 38 project grants worth a combined $46.8 million. Clinical trials are a key government priority, and this year's funding also supported eight national clinical trials, including a project called SENSAI, which studies a smartwatch early notification system for asthma interventions.
Dr. Young explained that oxygen is the most widely used therapy in intensive care, but growing evidence suggests that optimal oxygen levels vary between patients. The trial aims to shift intensive care from a "one-size-fits-all" model to personalised care through machine learning. He said that if successful, this research could fundamentally change how oxygen therapy is delivered in intensive care units worldwide, improving outcomes for thousands of critically ill patients each year, while demonstrating how AI can be safely and effectively integrated into routine clinical care, potentially paving the way for personalised treatments in other medical fields.
The research team will first use data from the recently completed Mega-ROX trial to optimise the machine learning model. The Mega-ROX trial, the largest ICU trial globally, involved 40,003 patients across 137 ICUs in 14 countries and was also funded by the HRC. The model will combine this data with personal information submitted by clinicians when patients are admitted to the ICU to assess the individual benefits or harms of using higher or lower oxygen levels for patients on life support. Next, researchers will compare personalised oxygen therapy plans where doctors decide oxygen levels with the help of machine learning, against standard methods where doctors work without AI assistance.
Dr. Young noted that the limitation of trials like Mega-ROX is that they can only measure the average treatment effect across a population. Applying the average to individual patients assumes a uniform benefit, which may not reflect clinical reality. The REVOLUTION trial, however, will use machine learning to identify the oxygen targets most likely to benefit each patient.
Of the 50 ICUs involved, 12 are located in New Zealand, expected to contribute approximately 7,000 patients. Australia has also secured funding to recruit the remaining patients from its local ICUs. The trial is expected to begin recruitment in 2028, targeting adult patients requiring unplanned life support in the ICU.
Dr. Stacey Pene, Investment Director and Acting Joint Chief Executive of the Health Research Council (HRC), stated that the trial bridges the gap between research and clinical practice at a national level, and has the potential to fundamentally change how clinical trial results are translated into patient care by combining machine learning with high-quality data from randomised clinical trials.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
