top of page
  • Writer's pictureAC

Chinese AI Beats Doctors Diagnosing

Updated: Oct 21, 2019

| AI + T |

A Chinese Artificial Intelligence system diagnosed brain tumors and other conditions more accurately and faster than a team of top Chinese physicians. The AI, called BioMind, was developed by the Artificial Intelligence Research Centre for neurological Disorders at Beijing Tiantan Hospital.

The AI correctly diagnosed 87 percent of 225 cases in just 15 minutes, while a team of 15 senior physicians diagnosed 66-percent of the cases accurately. When it came to predicting cases of brain hematoma expansion, the AI won yet again: with correction predictions in 83 percent of cases, whereas doctors only achieved 63-percent. And that’s not because the doctors were slacking. According to Gao Peiyi the head of radiology department at Tian Tian hospital, the human results were better than average accuracy in ordinary hospitals.

To train the AI, developers gave the AI tens of thousands of images and diagnoses from the hospital’s past ten years. The AI could diagnose a number of neurological diseases, including meningioma and glioma with over 90 percent accuracy. "I hope through this competition, doctors can experience the power of artificial intelligence. This is especially so for some doctors who are skeptical about artificial intelligence. I hope they can further understand AI and eliminate their fears toward it," Wang Yongjun, executive vice president of the Tiantan Hospital.

AI can reduce workloads for doctors and help them keep improving their skills. It would function like a GPS, while human physicians remain behind the wheels. According to Dr. Gauden Galea, a representative of the World Health Organization in China, China's huge population and accessible digital medical data gives it an advantage in developing medical AI.

12 views0 comments

Recent Posts

See All


Automous Technology, Artifficial Intelligence, Architecture, Design, Emerging, Blockchain, Cryptocurrency, Digital, Electric Vehicles, Science, Self-driven, Trends
bottom of page