How an AI system beat experienced doctors at diagnosing rare diseases
SMRTR summary
DeepRare, an AI system developed by Shanghai researchers, outperformed five experienced doctors in diagnosing rare diseases by correctly identifying conditions 64.4% of the time compared to doctors' 54.6% success rate. The system uses 40 specialized tools to mimic human diagnostic reasoning, analyzing patient data, medical literature, and genetic variants before ranking possibilities. With over 600 medical institutions now using the platform since July 2025, this breakthrough could significantly reduce diagnostic delays for 300 million people worldwide affected by rare diseases.
SMRTR provides this summary for quick context. The original article belongs to The Next Web.
Read the original article