Chinese robot beats 15 doctors in the diagnosis of brain tumors

The BioMind AI System, developed by the Artificial Intelligence Research Center for Neurological Disorders at this hospital and by a team from Capital Medical University, completed in 87 minutes 87% of the correct diagnoses (out of a total of 225) With regard to the prediction of cerebral hematoma, its accuracy was 83%, while doctors – from prestigious hospitals in the country – accounted for 63% of cases. In both tests, the level of accuracy of humans was "quite normal and better than average results in ordinary hospitals," said Gao Peiyi, head of the department of radiology at Tiantan Hospital. pointer in neurology and neurosurgery.

The robot has been formed over the last ten years by storing tens of thousands of images of diseases related to with the nervous system, which makes it able to diagnose common neurological diseases such as meningioma and the glioma with a precision rate of over 90%.

Vice President of the hospital, Wang Yongjun, pointed out that winner, because "the competition does not intend to confront humans with technology, but to help doctors learn and improve through interaction "with him, especially the more" skeptical ".

One of the participating doctors who was eliminated In the second round, Lin Yi said that he was looking forward to the use of artificial intelligence, which he does not consider as a threat but as "a friend".

The jury pointed out that artificial intelligence will never replace professionals, but it will work the same way as the use of a GPS by a driver.

EFE / OS