A team of international researchers has developed a man-made intelligence (AI) tool that may predict what quantity extra oxygen a COVID-19 patient might need during medical care.
To check the accuracy of the AI tool, it absolutely was tested call at variety of hospitals across five continents.
The results showed it predicted the oxygen needed within 24 hours of a patient’s arrival within 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 globe were analysed within the study published within the peer-reviewed medical journal Nature Medicine on Thursday.
The technique, called 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 every hospital so no data was shared or left its location.
Once the algorithm had ‘learned’ from the information, the analysis was brought together to make 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 within the UK, who led the study.
“Usually in AI development, after you create an algorithm on one hospital’s data, it doesn’t work well at the other hospital,” said study first author Ittai Dayan, from Mass General Bingham within the US.
By developing the model using objective, multimodal data from different continents, the researchers were ready to build a generalisable model which will help frontline physicians worldwide.
Bringing together collaborators across North and South America, Europe and Asia, the study took just period of AI ‘learning’ to attain high-quality predictions.
“Federated Learning allowed researchers to collaborate and set a brand new standard for what we are able to do globally, using the facility of AI,” said Mona G Flores, Global Head for Medical AI at healthcare technology company NVIDIA.
“This will advance AI not only for healthcare but across all industries looking to create robust models without sacrificing privacy,” Ms Flores said.
