andrewzamai/ADNI1234_allFTD_amyloidfiltered-splits-1p5345T-medianLobes-GRPO-upsampled

该数据集包含患者的主诉（subject）、文本报告（txt_report）和金标准诊断（gold_diagnosis）三个字段。数据集分为训练集、验证集和测试集，其中训练集包含3240个示例，验证集包含106个示例，测试集包含641个示例。数据集适用于医疗文本分析，特别是诊断相关任务。

The dataset includes three fields: patients chief complaint (subject), text report (txt_report), and gold standard diagnosis (gold_diagnosis). It is split into training, validation, and test sets, containing 3240, 106, and 641 examples respectively. The dataset is suitable for medical text analysis, particularly for diagnostic-related tasks.