A bunch of international researchers have developed an artificial intelligence tool that will help in detecting the amount of oxygen a Covid-19 patient might need during hospital surveillance. In order to check the credibility of the AI tool, researchers come in the way and survey the necessary Artificial Intelligence device in a number of hospitals across five continents.

Journal Nature Medicine on Thursday analysed the outcomes of nearly about 10,000 Covid-19  patients. Further an algorithm has been used to examine chest X-rays  and electronic health data of hospital patients showing covid-19 symptoms. Researchers named this technique as Âfederated learningÂ. The reports suggested that the oxygen needed within  24 hours of a patient’s arrival in an emergency ward constitutes 95% sensitivity and over 88% specificity. 

“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.

The multimodal data assisted the researchers to construct a generalisable model which will further become the support system of frontline physicians operating globally. The whole system was made ready within the timeline of  weeks to achieve high quality predictions. North & south America, Europe and Asia were the prime countries where collaborators were brought down to produce effective results and efficient techniques. 

ÂFederated 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

ÂThis will advance AI not just for healthcare but across all industries looking to build robust models without sacrificing privacy,” Ms. Flores said.
Continue Reading on The India Saga