Meet the algorithm that can diagnose pneumonia better than expert radiologists

CheXNet, a new algorithm developed by researchers at Stanford University, can diagnose 14 different medical conditions and was able to diagnose pneumonia better than the university’s own radiologists. The researchers say that, in the future, they hope the algorithm will be able to help providers without easy access to a radiologist.

“Interpreting X-ray images to diagnose pathologies like pneumonia is very challenging, and we know that there’s a lot of variability in the diagnoses radiologists arrive at,” Pranav Rajpurkar, a Stanford graduate student, told Taylor Kubota of Stanford News Service. “We became interested in developing machine learning algorithms that could learn from hundreds of thousands of chest X-ray diagnoses and make accurate diagnoses.”

A paper about the algorithm can be read here.

Click the link below for the full story from Stanford News Service.