Despite being widely praised by many of its users, ChatGPT recently left much to be desired by experts who compared the chatbot’s medical writing alongside that of seasoned professionals.

New data published in the American Journal of Roentgenology details the performance of a deep learning model known as BERT, short for Bidirectional Encoder Representations from Transformers.

Energy consumption reduction tactics could decrease greenhouse gas emissions owed to radiology while also saving departments tens of thousands of dollars every year. 

When tested, the model achieved a performance comparable to that of human experts.

The FDA-approved tool works by reprioritizing CTPA exams to the top of a radiologist’s work list when the scan is positive for PE.

These are factors that healthcare systems can and should control, experts recently suggested in a new JACR paper.

Radiologists used an AI tool-building platform to create their model(s), which allows clinicians the opportunity to develop AI models without any prior training in data sciences or computer programming. 

In a study that included hundreds of radiologist recommendations for additional imaging, there was a threefold increase in follow-up adherence when radiologists utilized a voluntary closed-loop communication tool that required structured recommendations.