Previous NLP algorithms for heart failure looked for certain words or phrases, but this updated model makes decisions based on clinical context. 

Nina Kottler, MD, associate CMO for clinical AI at Radiology Partners, explains the movement toward greater regulation of artificial intelligence and the need to test for bias. 

The healthcare market analysis firm Signify Research released a list of predictions in radiology its analysts expect to see in 2025. 

Recommendations for additional imaging are routinely included in radiology reports but are sometimes overlooked or not communicated in a timely manner. Experts believe large language models can help address these lapses in care. 

The agency said Contec and Epsimed monitors connected via WiFi are particularly susceptible to cyberattack and could be used to gain access to hospital systems. 

Researchers estimate that it could cost less than $0.01 per report to use the large language model as a radiology report proofreader. 

Radiology researchers have developed and validated an automated program for tracking incidental imaging findings. The system facilitates communications between radiologists, patients and primary care providers whenever such findings turn up.  

The University of Pennsylvania in Philadelphia has aimed to tackle this conundrum, developing a deep learning-based image analysis tool and AI “orchestrator.”