HRC Programme Grant Supports MRINZ-Led World-First AI Intensive Care Research

The Health Research Council of New Zealand (HRC) has awarded the MRINZ one of only two Programme Grants funded nationally in 2026, supporting a world-first clinical trial that will investigate whether artificial intelligence (AI) can improve outcomes for critically ill patients receiving life support in intensive care units (ICUs).

Led by Professor Paul Young, MRINZ Deputy Director and Co-Clinical Leader of ICU at Wellington Hospital, the five-year research programme will evaluate whether machine learning can help clinicians personalise oxygen therapy for patients receiving life support.

The REVOLUTION trial will involve 50 ICUs across New Zealand and Australia and recruit more than 24,000 patients, making it one of the largest critical care studies undertaken in Australasia. It will be the first major clinical trial worldwide to test whether AI-guided treatment using machine learning improves survival in the ICU.

The research builds on the recently completed HRC-funded Mega-ROX trial, the world's largest ICU oxygen trial, which involved 40,000 patients across 125 sites in 15 countries.

Oxygen is the most widely used therapy in intensive care, with around 20 million people worldwide requiring life support each year. Researchers will use machine learning to estimate the individual benefit — or harm — of higher versus lower oxygen levels for patients on life support, helping clinicians determine the most appropriate oxygen target for each person.

Professor Young says the programme aims to move critical care beyond a one-size-fits-all approach.

“We aim to use machine learning to transform critical care from a ‘one-size-fits-all’ model to a personalised care model that ensures everyone is treated fairly and equitably,” says Professor Young.

“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.”

Researchers will compare outcomes between patients whose oxygen therapy is guided by machine learning-assisted recommendations and those receiving standard care, where oxygen levels are determined without AI support.

If successful, the trial could establish an international benchmark for the safe, transparent and rigorous use of AI-derived models in clinical decision-making.

Professor Young says the potential impact of the research extends far beyond New Zealand.

“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 says the study has the potential to transform how clinical trial findings are translated into patient care.

“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,” says Mr Pene.

The HRC Programme Grant will support the New Zealand component of the trial, while Australia's National Health and Medical Research Council (NHMRC) will support the Australian component.

Read the full Health Research Council of New Zealand media release here.