Researchers in the U.S. and China have developed a system that uses artificial intelligence (AI) to automatically diagnose common childhood conditions after considering patients' symptoms, history, laboratory results, and other clinical data.
The researchers said during testing, the system was highly accurate, and could one day assist doctors in diagnosing complex or rare conditions.
They trained the system on medical records from nearly 600,000 Chinese patients who had visited a pediatric hospital over an 18-month period.
The system uses a neural network to recognize patterns in text, as well as in medical images.
When tested on unlabeled data, the software could approach the performance of experienced physicians, achieving an accuracy rate of more than 90% for diagnosing asthma; the accuracy of physicians in the study ranged from 80% to 94%.
From The New York Times
View Full Article - May Require Paid Subscription
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA