This new AI system can prioritize x-rays by urgency
X-rays are one of the most widely used diagnostic tools used in the world, accounting for 40% of all diagnostic imaging used worldwide. Hence, due to its wide use, people usually have to wait for a good amount of time until they get their results. Here’s where artificial intelligence comes to play. The technology has promised to reduce waiting times substantially.
Scientists at the University of Warwick have published a study in the Journal Radiology, discussing a new AI technology that can prioritize x-ray scans. This means that it would automatically pick out the scans that are in the most urgent need for attention and prioritize them over the others.
Giovanni Montana, the co-author of the study, said, “Currently there are no systematic and automated ways to triage chest x-rays and bring those with critical and urgent findings to the top of the reporting pile.” The researchers working on this project used 470,388 adult chest X-rays to build an AI system that could identify key issues.
The system was fed specific abnormalities on x-rays so that it could classify them on the basis of “critical,” “urgent,” “non-urgent,” or “normal.” The researchers tested the system’s performance in a simulation using a set of 15,887 images. The AI system differentiated between abnormal and normal chest X-rays with high accuracy.
Professor Montana also stated, “With further clinical validation, this technology is expected to reduce a radiologist’s workload by a significant amount by detecting all the normal exams so more time can be spent on those requiring more attention.”
The researchers also intend to expand their research so it would include a much larger sample size. They also plan on working on more complex algorithms so that the accuracy of the technology can be improved.