Upon second inspection, 371 (58.3%) of the 636 chest X-rays were classified as normal. Of the 265 (41.7%) re-read as abnormal, 195 were classified as mild disease, 65 as moderate, and 5 as severe.

Two freely available chest X-ray datasets were used to test and train the AI model. The datasets comprised three categories of chest X-ray images: normal, coronavirus-positive, and viral pneumonia.

Of the 429 chest X-rays that were classified as normal, 120, or 28%, were also classified by the AI tool as normal. These X-rays, or 7.8 % of all the X-rays, could be potentially safely automated ...

A chest X-ray, is an X-ray of the chest, just as it sounds and you can see a number of things on the chest X-ray. ... So a whole lot more of X-ray gets through the lungs under normal circumstances.

An AI chest x-ray reader could provide near instantaneous interpretations. And AIs will never need to take lunch breaks or get distracted by noisy working conditions or complain about working 24 ...