Researchers looking for untapped uses for AI have turned to their attention to mechanical ventilation of patients, with a recent, in-depth review of studies that has helped clarify both the current use of AI and how it might help guide providers considering putting patients on mechanical ventilation.
Led by clinicians at the UK’s Guy's and St Thomas' NHS Foundation Trust, reviewers found 1,342 papers on AI and mechanical ventilation and looked in detail at 95 of these. Many of the
studies, they found, were looking at early testing of AI technology and models, while one was already at the next stage of clinical trials in patients, with others soon to follow.
"Our systematic review of the literature revealed an exponential increase in the rate of publications on artificial intelligence as applied to mechanical ventilation in the past few years,” said Dr. Luigi Camporota, a consultant in intensive care medicine at Guy's and St Thomas’. “Despite this increased scientific and clinical interest, artificial intelligence is still very little used in mechanical ventilators.”
Mechanical ventilation is increasingly considered an area where AI could help guide treatment decisions, as patients put on mechanical ventilation can vary hugely. Consequently, AI may help to personalize approaches to an individual's characteristics, while also potentially being used to flag to a clinician exactly when a person should be taken off or put on to ventilation.
AI “has the potential to improve the management of mechanical ventilation therapy,” Dr. Jack Gallifant, from the Centre for Human and Applied Physiological Sciences at King's College London, summed up the team’s conclusions. “Our review highlights a need for greater code and data availability, and thorough validation that, combined with smaller bias, will facilitate translation of data science into improved patient care.”
The team of academics at Guy’s and St Thomas’ and King’s College London made recommendations for further transparency, to help avoid bias and to facilitate rapid developments in this field. They also made recommendations for researchers to improve work in the field, including improving the availability of data. They also recommended better reporting of characteristics like ethnicity and gender, to help scientists assess how well findings can be generalized across wider populations.
The researchers were supported by grants from the National Institute for Health Research, Wellcome Trust, the National Institute of Academic Anaesthetists and the Royal Academy of Engineering. Their report was published at the British Journal of Anaesthesia.
Photo by Ekkasit919/Getty Images