Determining how to reimburse for healthcare artificial intelligence is likely to be a “complex policy challenge,” CEO William T. Thorwarth Jr., MD, wrote May 6. 

Buzzworthy developments of the past few days.

Four of five hospital leaders trust the accuracy of their institution’s data. Yet almost half of useable data gets underutilized if not completely untapped for guiding business and clinical decisions.

Finely tuned, pre-trained large language models are beginning to reliably translate image content into text, but are they ready to take on medical images? 

The combination of AI and CT helped Nehal Mehta, MD, and colleagues track the performance of a new drug designed to target coronary inflammation. 

Machine learning models could help create a more standardized, reproducible and efficient way of grading Crohn’s disease severity in the small bowel based on CT imaging. 

The popular AI chatbot's performance highlighted both its strengths and its weaknesses. It can answer multiple-choice questions, for example, but it struggles with consistency. 

The model was developed and validated specifically for liver, spleen and pancreas segmentation, and outperformed a publicly available segmentation model already in use.