By Stephen Beech via SWNS
Artificial intelligence can help spot early signs of cancer in chest x-rays, according to a new study.
Scientists found that a state-of-the-art AI tool can identify normal and abnormal chest x-rays in a clinical setting.
Scientists said that an AI tool could accurately differentiate between normal and abnormal chest x-rays. (Photo via SWNS)
Chest X-rays are used to diagnose several conditions to do with the heart and lungs.
An abnormal chest X-ray can be an indication of a range of conditions, including cancer and chronic lung diseases.
Scientists say that an AI tool that can accurately differentiate between normal and abnormal chest X-rays would greatly reduce the heavy workload of radiologists.
Study co-author Dr. Louis Lind Plesner said: “There is an exponentially growing demand for medical imaging, especially cross-sectional such as CT and MRI.
“Meanwhile, there is a global shortage of trained radiologists.
“Artificial intelligence has shown great promise, but should always be thoroughly tested before any implementation.”
Dr. Plesner and his colleagues wanted to determine the reliability of using an AI tool that can identify normal and abnormal chest X-rays.
They used a commercially available AI tool to analyze the chest X-rays of 1,529 patients from four hospitals in Denmark.
Chest X-rays were included from emergency department patients, in-hospital patients and outpatients.
The X-rays were classified by the AI tool as either “high-confidence normal” or “not high-confidence normal,” as in normal and abnormal, respectively.
Two board-certified radiologists were used as the reference standard. A third radiologist was used in cases of disagreements.
Of the 429 chest X-rays that were classified as normal, 120 (28 percent) were also classified by the AI tool as normal. Those X-rays – 7.8 percent of the total – could be potentially safely automated by an AI tool.
The AI tool identified abnormal chest X-rays with a 99.1 percent of sensitivity.
Dr. Plesner, from the Department of Radiology at the Herlev and Gentofte Hospital in Copenhagen, said: “The most surprising finding was just how sensitive this AI tool was for all kinds of chest disease.
“In fact, we could not find a single chest X-ray in our database where the algorithm made a major mistake.
“Furthermore, the AI tool had a sensitivity overall better than the clinical board-certified radiologists.”
He said the AI tool performed particularly well at identifying normal X-rays of the outpatient group at a rate of 11.6 percent.
Dr. Plesener said the findings, published in the journal Radiology, suggest that the AI model would perform especially well in outpatient settings with a high prevalence of normal chest X-rays.
He added: “Chest X-rays are one of the most common imaging examinations performed worldwide.
“Even a small percentage of automatization can lead to saved time for radiologists, which they can prioritize on more complex matters.”
The editorial on the topic praised the potential to take care of 7.8% of all the normal readings for the radiologists, one of the key findings of the study, but suggests that as a labor-saving device, more research is needed to ensure radiologists aren’t putting patients at risk for a mere 7.8% reduction in workload.