Johns Hopkins radiologists have repurposed a deep learning algorithm designed to detect tuberculosis on chest x-rays to, instead, help identify COVID-19.

The European Union has certified AI software for reading mammograms, clearing the way for a South Korea-based AI vendor to sell another of its AI products across the European Economic Area.

If a medical AI algorithm performs well, why let the proverbial black box undermine confidence in it?

 

Healthcare providers are still asking the Trump administration for help securing personal protective equipment (PPE) as they continue to care for COVID-19 patients.

As part of its $5 million pandemic response, Amazon is placing more than 8,000 of its Echo Dot devices across dozens of senior-living facilities in parts of California and Washington State.

It was late April when the CDC added impaired taste and/or smell to its list of COVID-19 symptoms. Thanks to AI and natural language processing (NLP), researchers at the Medical University of South Carolina had beaten the federal agency to the punch.

AI enthusiasts have varying aims and incentives for pushing the technology into healthcare, but many parrot a common set of justifications. Do any of these sound familiar?

Researchers have demonstrated a way to visually explore small-molecule inhibitors that, according to algorithmic suggestions, show potential for targeting COVID-19’s main proteins.