MMADE

MMADE数据集由印度理工学院帕特纳分校计算机科学与工程系创建，包含1500个与药物副作用相关的文本和图像对。数据集通过收集社交媒体、医疗博客和病例报告中的信息构建，旨在通过结合文本和图像信息提高药物副作用检测的准确性。该数据集的应用领域包括药物副作用分类、描述生成和摘要任务，旨在通过视觉和文本信息的结合，提升医疗专业人员在诊断和治疗规划中的精确性，从而增强患者安全和医疗沟通。

The MMADE dataset was created by the Department of Computer Science and Engineering, Indian Institute of Technology Patna, and contains 1500 text-image pairs related to adverse drug reactions. It was constructed by collecting information from social media, medical blogs and case reports, aiming to improve the accuracy of adverse drug reaction detection by integrating both textual and visual information. Its application scenarios include adverse drug reaction classification, caption generation and summarization tasks. Through the combination of visual and textual information, it is designed to enhance the precision of medical professionals in diagnosis and treatment planning, thereby improving patient safety and medical communication.