PyTrial

PyTrial数据集是由伊利诺伊大学厄巴纳-香槟分校计算机科学系的研究团队开发的，专注于临床试验应用的机器学习软件和基准。该数据集包含23个机器学习就绪的数据集，用于快速实施和测试。PyTrial定义了临床试验设计与操作中的六个主要任务，包括患者结果预测、试验站点选择、试验结果预测、患者-试验匹配、试验相似性搜索和合成数据生成。这些数据集旨在通过提供标准化的数据加载、模型规范、模型训练和模型评估流程，简化并加速机器学习在药物开发中的研究。

The PyTrial dataset is developed by a research team from the Department of Computer Science at the University of Illinois Urbana-Champaign, focusing on machine learning software and benchmarks for clinical trial applications. It contains 23 machine learning-ready datasets for rapid implementation and testing. PyTrial defines six core tasks in clinical trial design and operations, including patient outcome prediction, trial site selection, trial result prediction, patient-trial matching, trial similarity search, and synthetic data generation. These datasets aim to simplify and accelerate research on machine learning applications in drug development by providing standardized workflows for data loading, model specification, model training, and model evaluation.