Artificial intelligence (AI) tools should always be tested across “a wide range of populations,” according to new research published in PLOS Medicine. The authors shared this warning after seeing some models perform worse when tested on data from an outside health system. 

A majority of patients in the United States who undergo a diagnostic imaging procedure are satisfied with the overall experience, according to the results of a new survey conducted by Healthcare Research Worldwide. However, approximately half of those patients feel anxious leading up to actual examination.

Implementing locally developed appropriate use criteria (AUC) as clinical decision support (CDS) could help reduce unnecessary imaging for emergency department (ED) patients with renal colic, according to new research published in the American Journal of Roentgenology.

MaxQ AI’s Accipio Ix intracranial hemorrhage (ICH) detection software has gained FDA clearance, the company announced this week.

Wikipedia contains a significant number of articles and images that could be incorporated into the Patient-Oriented Radiology Reporter (PORTER) initiative, according to new research published in the Journal of Digital Imaging. This could then help patients understand the information included in their radiology reports. 

Visla Labs, a San Francisco, California-based startup focused on the use of artificial intelligence (AI) in radiology, has raised $3 million in funding to “grow its team, scale product features, attain regulatory approval and fuel expansion and growth.”