Artificial Intelligence is getting smarter every day and its applications are getting wider than some gimmicky features on a smartphone. AI is also being used in the field of medical science for one. And recently, a group of researchers have created an AI system that can accurately detect pneumonia in just 10 seconds.
Getty Images/ Reuters
The system was developed by researchers from Intermountain Healthcare and Stanford University. According to them, the prompt action of AI can help doctors diagnose pneumonia in a patient faster than standard clinical procedures and help save lives.
In a usual procedure, patients suspected of having pneumonia are asked to get a chest X-ray. While they get made in no time, the time to detect the presence of pneumonia by radiologists can take 20-minutes, even more. This delays the time-sensitive treatment pneumonia patients need.
Dubbed the CheXpert system, it was developed by Stanford Machine Learning Group that trained the AI using 188,000 chest-images (taken from the Stanford Medical Center in Palo Alto, Calif) to help it differentiate between what looks like pneumonia and what doesn't.
Moreover, as patients come from different geographic locations, researchers then fine-tuned CheXpert specifically for Utah, by scanning another 6973 images from Intermountain Emergency departments.?
Representative Image: Rawpixel
According to Jeremy Irvin, a PhD student at Stanford and a member of the research team, "We've been developing a deep learning algorithm that can automatically detect pneumonia and related findings in chest X-rays. In this initial study, we've demonstrated the algorithm's potential by validating it on patients in the emergency departments at Intermountain Healthcare. Our hope is that the algorithm can improve the quality of pneumonia care at Intermountain, from improving diagnostic accuracy to reducing time to diagnosis."
According to Nathan C. Dean, MD, principal investigator of the study, and section chief of pulmonary and critical care medicine at Intermountain Medical Center in Salt Lake City, CheXpert model will soon be applied in live emergency departments, on select Intermountain Healthcare Hospital by this fall. They were also the ones to fund the research.