Despite the inroads AI has made into many medical specialties, the technology has failed to find a foothold in primary care. Why is that?

How has digital health contributed to the fight against COVID-19? What kinds of outcomes has it produced? What have been some unintended consequences of its deployment?

Fresh off an investment infusion of $25 million, a tech startup has launched an ambitious virtual consortium to seek “breakthrough medical discoveries and actionable findings” for the global battle against COVID-19. 

The University of Pennsylvania is teaming with Intel to lead a federation of more than two dozen medical and research centers on an AI system for identifying brain tumors.

Researchers in the U.K. and U.S. have developed an automatic prediction model that can tell if someone is infected with COVID-19 based on symptoms alone.

The aim of the collaboration is to map out cardiac irregularities caused by the virus.

A convolutional neural network trained and internally validated on more than 15,000 lung CT scans has correctly reclassified indeterminate pulmonary nodules into low-risk or high-risk categories.

The FDA has permitted the use of Aidoc’s AI models for the detection and prioritization of incidental CT findings associated with COVID-19.

When applying AI to help answer clinical questions, developers, researchers and clinicians should all remain mindful of the difference between interpretability and explainability.

AI developers working to refine COVID-19 detection in chest x-rays must navigate two unavoidable speed bumps.