A team of US health tech specialists this week announced a new programme to use artificial intelligence to scan 24,000 papers on COVID-19 to find patterns, signs and insights about the virus.
The aim is to help to find answers to questions raised by the World Health Organisation about the pandemic.
The dataset includes over 20,000 papers that will made available, know as COVID-19 Open Research Dataset. It is calling on researchers, tech organisations, data mining and machine language experts to help explore the use of AI to understand patterns in the research.
Last week’s article on AI in mental health partially covered how AI can be used to analyse language within texts and in doing so, identify those ‘at risk’ of depression.
The idea behind close reading of text, or content analysis, is to find patterns, signs and meaning in order to answer posed questions. The data will be made available on a website where experts in data and AI can make proposals of tools and code to use to unearth insights from the texts. Using machine learning to analyse text drastically reduces the amount of time taken compared to human analysis.
The project includes the National Library of Medicine, Microsoft, Allen Institute of AI, Georgetown University’s Centre for Security and Emerging Technology, the Chan Zuckerberg Initiative, and Kaggle, which is a part of Google.
Cofounder and CEO of Kaggle, Anthony Goldbloom said “It’s difficult for people to manually go through more than 20,000 articles and synthesize their findings.”
“Recent advances in technology can be helpful here. We’re putting machine readable versions of these articles in front of our community of more than 4 million data scientists.”
“Our hope is that AI can be used to help find answers to a key set of questions about COVID-19.”
The database will be hosted by the Allen Institute’s Semantics Scholar website.
Head of science at the Chan Zuckerberg Initiative, Cori Bargmann said “Sharing vital information across scientific and medical communities is key to accelerating our ability to respond to the coronavirus pandemic.”
“The new COVID-19 Open Research Dataset will help researchers worldwide to access important information faster.”