A group of researchers in the U.S. and China developed an artificial intelligence (AI) system that automatically diagnoses common childhood conditions — from influenza to meningitis — after processing the patient’s symptoms, history, lab results, and other clinical data. According to their study findings, which were published in Nature Medicine, the AI system produced accurate diagnoses at a similar rate to physicians.
Drawing on the records of nearly 600,000 patients who had visited Guangzhou Women and Children’s Medical Center over an 18-month period, Chinese researchers fed large amounts of patient data into the AI system. The system was more than 90 percent accurate in diagnosing asthma; physicians’ accuracy ranged from 80 to 94 percent.
“In some situations, physicians cannot consider all the possibilities,” Kang Zhang, MD, chief of ophthalmic genetics at the University of California, San Diego, told The New York Times. “This system can spot-check and make sure the physician didn’t miss anything.”
Although the findings are promising, replicating this study in the U.S. would be difficult given that the average hospital is smaller, and regulations make it difficult to pool data from multiple facilities. President Trump recently signed an executive order meant to spur the development of AI technologies. As part of the initiative, the administration will encourage federal agencies and universities to share data.
Source: The New York Times, February 11, 2019.