302 Rare Disease Cases Dataset

*This dataset supports online use.Click here to jump.

This dataset is from the paperEnhancing diagnostic capability with multi-agents conversational large language models"The test set used in this study has been accepted by Nature.

The dataset contains 302 rare diseases, with 1 to 9 rare diseases randomly selected from each category. These rare diseases were selected from 7k+ rare diseases in 33 types in the Orphanet database, a comprehensive rare disease database co-funded by the European Commission. Since rare diseases are distributed differently in different types, a normalized weighted random sampling method was used to select them to ensure balanced representation. The sampling weights were adjusted according to the number of diseases in each type and adjusted by natural logarithm transformation.