AUC: area under the curve, FPF: false positive fraction, TNF: true negative fraction, TPF: true positive fraction, FNF: false negative fraction, PPV: Positive predictive value, NPV: Negative predictiv

NIAID Data Ecosystem20

yesilhealth/Health_Benchmarks

医疗AI评估

医学问答系统

该数据集是一个专门用于评估大型语言模型（LLM）在医疗保健领域的性能的资源。数据集包括50多个医疗和健康相关主题的结构化问答对，旨在测试AI模型在理解和发展特定领域的知识方面的表现。数据集按医疗专业和子领域组织，每个专业领域都有问题和相应的高质量答案。数据集适用于LLM评估、医疗保健AI研究和医疗教育AI系统。

Hugging Face2025-04-20 更新50

Mean Specificity, Sensitivity, PPV, NPV and Percentage of selected persons (PSP) for 1000 holdout evaluations with corresponding 95% confidence intervals for a set of common variables.

测试评估

分类模型验证

Mean Specificity, Sensitivity, PPV, NPV and Percentage of selected persons (PSP) for 1000 holdout evaluations with corresponding 95% confidence intervals for a set of common variables.

NIAID Data Ecosystem20

Performance comparison between the proposed AI system and resident test.

资源简介：

相关数据集