A team of international researchers has developed an artificial intelligence (AI) tool that can predict how much extra oxygen a COVID-19 patient might need during hospital care.
To check the accuracy of the AI tool, it was tested out in a number of hospitals across five continents.
The results showed it predicted the oxygen needed within 24 hours of a patient's arrival in the emergency department, with a sensitivity of 95 per cent and a specificity of over 88 per cent.
The outcomes of around 10,000 COVID-19 patients from across the world were analysed in the study published in the journal Nature Medicine on Thursday.
The technique, known as federated learning, used an algorithm to analyse chest X-rays and electronic health data from hospital patients with COVID-19 symptoms.
To maintain strict patient confidentiality, the patient data was fully anonymised and an algorithm was sent to each hospital so no data was shared or left its location.
Once the algorithm had 'learned' from the data, the analysis was brought together to build the AI tool.
"Federated learning has transformative power to bring AI innovation to the clinical workflow," said Professor Fiona Gilbert, from the University of Cambridge in the UK, who led the study.
"Usually in AI development, when you create an algorithm on one hospital's data, it doesn't work well at any other hospital," said study first author Ittai Dayan, from Mass General Bingham in the US.
By developing the model using objective, multimodal data from different continents, the researchers were able to build a generalisable model that can help frontline physicians worldwide.
Bringing together collaborators across North and South America, Europe and Asia, the study took just two weeks of AI 'learning' to achieve high-quality predictions.
"Federated Learning allowed researchers to collaborate and set a new standard for what we can do globally, using the power of AI," said Mona G Flores, Global Head for Medical AI at healthcare technology company NVIDIA.
"This will advance AI not just for healthcare but across all industries looking to build robust models without sacrificing privacy," Flores said.