Stanford researchers have developed a deep-learning algorithm capable of diagnosing up to 14 different medical conditions, and it is able to diagnose pneumonia better than expert radiologists. They call it CheXNet, and it has the potential to drastically reduce the number of misdiagnoses.
“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,” said Pranav Rajpurkar, a graduate student in the Machine Learning Group at Stanford and co-lead author of the paper. “We became interested in developing machine learning algorithms that could learn from hundreds of thousands of chest X-ray diagnoses and make accurate diagnoses.”
Why use algorithms?
Often, treatments for common but devastating diseases that occur in the chest, such as pneumonia, rely heavily on how doctors interpret radiological imaging. But even the best radiologists are prone to misdiagnoses due to challenges in distinguishing between diseases based on X-rays.
CheXNet also has a feature that produces what looks like a heat-map of the chest, identifying areas most likely to contain pneumonia and directing radiologists to those areas right away. This could lead to faster diagnoses for patients where the time factor is paramount.
“We plan to continue building and improving upon medical algorithms that can automatically detect abnormalities and we hope to make high-quality, anonymized medical datasets publicly available for others to work on similar problems,” said Jeremy Irvin, a graduate student and co-lead author of the paper. “There is massive potential for machine learning to improve the current health care system, and we want to continue to be at the forefront of innovation in the field.”