A major clinical trial involving 50 hospital intensive care units (ICUs) throughout New Zealand and Australia is set to test whether artificial intelligence (AI) can help doctors save more lives of patients who are on life support.
Clinical researcher Professor Paul Young, Deputy Director of the Medical Research Institute of New Zealand and Co-Clinical Leader of the ICU at Wellington Hospital, received a $5 million Programme Grant from the Health Research Council of New Zealand (HRC) to lead the trial, which will look to recruit more than 24,000 patients.
The ‘REVOLUTION trial’ would be the first major clinical trial worldwide to evaluate whether AI guided treatment using machine learning improves survival in the ICU and could set an international benchmark for safe, transparent and rigorous application of AI-derived models in clinical decision-making.
Funding from the HRC would support the New Zealand component of the trial, while the NHMRC will fund the Australian component.
Prof Young said his team would use machine learning to evaluate the best targets for delivering oxygen to patients on life support in ICUs, noting about 20 million people require life support around the world each year, with oxygen the most widely used ICU therapy.
Prof Young said they would first refine and optimise their machine learning model using data from their recently completed HRC-funded Mega-ROX trial – the world’s largest ICU trial involving 40,003 patients from 137 ICUs in 14 countries.
The model would use this data, together with personal data submitted by clinicians when patients are admitted to the ICU, to estimate the individual benefit – or harm – of higher versus lower oxygen levels for patients on life support.
From there, they would compare the personalised delivery of oxygen treatments to patients when doctors use machine learning to help them decide what level of oxygen each patient receives, versus the standard approach when doctors decide the oxygen level without AI.
“We aim to use machine learning to transform critical care from a ‘one-size-fits-all’ model to a personalised care model,” Prof Young said.
“It is easy to imagine a scenario where a treatment benefits a population ‘on average’ but where only a small group of patients benefit greatly, and most are in fact harmed. Machine learning could provide the information clinicians need to ensure they give the treatment only to those patients who will benefit and not to those who will be harmed.”
Prof Young said the potential global public health benefits of using AI to optimise a common therapy like oxygen for patients who need life support in the ICU were “profound.”
“By implementing our findings, hundreds of thousands of lives could be saved each year in ICUs around the world, even if our trial confirms only a modest reduction in deaths.”
HRC Director of Investments and Co-Chief Executive (acting) Mr Stacey Pene said the clinical trial involves every major ICU in New Zealand, “bridging the gap between research and clinical practice nationwide.”
“This study has the potential to fundamentally change the way clinical trial results are translated into patient care by integrating machine learning with high-quality data from a randomised clinical trial,” Mr Pene said.
“It also provides a unique opportunity for training the next generation of ICU researchers and clinician-scientists, ensuring that New Zealand retains and develops the necessary skills to address critical health issues.”
The trial is one of two Programme Grants (combined value of $10 million) and 38 Project Grants (combined value of $46.8 million) announced by the HRC.
Mr Pene said clinical trials were a key priority for the Government and this year’s Programme and Project Grants funding rounds support eight clinical trials across the country.
“The majority of these Programme and Project Grants support the development and retention of the clinician researcher workforce in New Zealand by including clinician researchers as members of the research team. Strengthening engagement with clinicians will help ensure treatments are used more effectively to deliver better outcomes for patients,” Mr Pene said.
The wider grants cover a range of Government’s priority health areas – including supporting new models of care and treatments for cancer and mental health and addiction.
Add Comment