Artificial Intelligence Spots COVID-19 In Chest X-rays
Designed for times of testing shortages, a UK research team has created an artificial intelligence-based computer model capable of finding COVID-19 in X-rays, according to Pharmaphorum.
Computer and machine vision students at Cranfield University built the system to utilize computer vision and AI. The model allows specialists to spot patterns undetectable to the human eye. The results indicate differences within the lungs that can infer pneumonia. Although pneumonia can be caused by a variety of diseases, the model is able to determine the source of the problem, whether it be COVID-19 or not. The model makes use of conventional machine learning algorithms and deep learning frameworks and posted results “with great accuracy.”
Leading the team is Cranfield computational engineering lecturer Dr. Zeeshan Rana. Dr. Rana said, “The research carried out in this pilot project has led to some extremely promising results and we are looking to build on this success rapidly to help in the fight against COVID-19.”
Other AI applications also contributed to the crucial fight against COVID-19. BenevolentAI (UK) identified Eli Lilly’s rheumatoid arthritis therapy Olumiant (baricitinib) as a potential treatment. The drug existed before the pandemic and was pushed into a clinical trial for COVID-19 in February by the U.S. National Institute for Allergies and Infectious Diseases.
Exscientia, based in Oxford, proved to be the first company using AI to successfully identify a drug admitted for human trial. Now, the company is searching through 15,000 different drugs in partnership with the Scripps research institute to combat SARS-CoV-2, the virus that COVID-19 comes from.