A group of researchers in the United States and China might have just built a system that could assist doctors in diagnosing condition and performs almost as accurately as human assistants.
According to an article published by The New York Times, the researchers tested the system equipped with artificial intelligence (AI) that could automatically diagnose common childhood conditions after processing the patient’s symptoms, history, lab results and other clinical data.
The test shows that the system is highly accurate and might be a potential assistant to doctors as it was able to diagnose asthma with 90 percent accuracy as compared to physicians’ 80 to 94 percent accuracy rate.
Meanwhile, the system was also 87 percent accurate in diagnosing gastrointestinal disease as compared to physicians’ 82 to 90 percent accuracy.
“In some situations, physicians cannot consider all the possibilities. This system can spot-check and make sure the physician didn’t miss anything,” said Dr. Kang Zhang, chief of ophthalmic genetics at the University of California.
Dr. Zhang and his team trained the system using electronic medical records of nearly 600,000 patients at the Guangzhou Women and Children’s Medical Center in southern China.
Despite its competent performance, Ben Shickel, a researcher at the University of Florida who specializes in the use of deep learning for health care said that Dr. Zhang’s system needs extensive clinical trials before entering the medical field.
“Medicine is a slow-moving field. No one is just going to deploy one of these techniques without rigorous testing that shows exactly what is going on,” said Shickel.
(Photo source: pressfrom.info/ deccanherald.com)
