AI has a long way to go before it meaningfully closes disparities in healthcare access and delivery. In fact, even when aimed at that goal, the technology can backfire. 

AI has already made a massive impact on healthcare, especially in the fields of cardiology and radiology. With the FDA clearing more and more algorithms, this trend is only expected to grow as time goes on.

As the use of AI in imaging continues to grow, it’s “become clear" that real world performance of these products can defer from premarket testing, experts note. 

Manisha Bahl, MD, explained that ChatGPT and other large language models offer significant potential to help radiologists with breast imaging exams, but they are "not quite ready for primetime."

Researchers developed several new AI models that could guide the management of patients with non-valvular atrial fibrillation. There is still some work to do in terms of accuracy, but they already appear to outperform the traditional risk scores being used today.

Meet an 86-year-old IT entrepreneur who recently beefed up his AI skills in a challenging postgraduate program. 

If the Trump administration continues taking a laissez-faire stance toward AI—including AI used in healthcare—why not let the states go it alone on regulating the technology? 

In a prospective study involving 54 adults, ultralow-dose CT, denoised with deep learning, “substantially” cut radiation exposure while accurately detecting pneumonia.