May 11, 2021

expert reaction to study looking at using machine learning and AI to identify which clinical parameters predict responses in critically ill COVID-19 patients

A study published in Intensive Care Medicine looks at the use of artificial intelligence (AI) methods to predict outcomes of critically ill COVID-19 patients using routine clinical information used by intensive care unit (ICU) medics.

Prof Derek Hill, Professor of Medical Imaging Science, UCL, and expert in medical devices, said:

“This study uses computational machine learning algorithms to analyse retrospective data from more than 600 COVID patients who were admitted to intensive care (ICU) during the first wave of COVID in the UK, more than 40% of whom died.  This research provides some insights into the way that treatment decisions in the first few days in ICU impacted outcomes, and which treatment decisions were associated with change in mortality.  A particularly striking finding is that at the peak of the pandemic mortality was higher and this may be because workload pressure resulted in “poor implementation” of treatment guidance.

“It is important to realise that the authors have not shown that their algorithm can be used to improve patient outcomes in subsequent waves of COVID, nor that artificial intelligence can help doctors manage heavy workloads in the peak of a pandemic.  In practice, changes in the way patients present and are treated since the start of the COVID pandemic means any algorithms that learn from the first wave will only have limited value in helping manage later COVID surges or surges in other countries.  A great deal more validation would be needed before an algorithm like this could be used to support clinical decision making.”

‘Natural history, trajectory, and management of mechanically ventilated COVID‑19 patients in the United Kingdom’ by Brijesh V. Patel et al. was published in Intensive Care Medicine on Tuesday 11 May 2021.

DOI: 10.1007/s00134-021-06389-z

All our previous output on this subject can be seen at this weblink:

www.sciencemediacentre.org/tag/covid-19

Declared interests

Prof Derek Hill: “No conflict of interest.”