2026-03-13
12 分钟The world is changing fast that you can learn it at a slower pace.
Special English Please note that the following stories are read by AI,
but all information has been written and verified by professional editors.
You are listening to Special English.
A Chinese research team has developed an AI-powered rare disease diagnostic system called DeepRare,
setting a new record for diagnostic accuracy.
The study has been published in the journal Nature.
The diagnosis and treatment of rare diseases have long faced challenges in confirming cases without genetic testing,
particularly in regions with limited access to such services.
Meanwhile,
traditional medical AI diagnostic systems often encounter trust issues due to their non-traceable reasoning processes.
The evidence-based DeepRare was developed by a team from Xinhua Hospital affiliated with the Shanghai Jiao Tong University's School of Medicine and the University's School of Artificial Intelligence
since its online diagnostic platform was launched last July.
It has registered over 1,000 professional users across more than 600 medical and research institutions worldwide.
Test data show that when only patients' clinical phenotypic information was provided without genetic data,
DeepRARE achieved a first attempt accuracy of 57% in phenotypic diagnosis,
an improvement of nearly 24 percentage points over the previous global model.
When genetic data were incorporated, its diagnostic accuracy exceeded 70%.
according to the study.
DeepRARE integrates real-time access to a vast repository of medical literature knowledge and real-world clinical case data.