相关数据集
3D-MIR
3D-MIR数据集是由微软健康与生命科学团队创建的,专注于3D医学图像检索的基准数据集。该数据集包含281个来自CT扫描的3D图像,涵盖肝脏、肺、胰腺和结肠四个器官系统。数据集的构建过程涉及使用TotalSegmentator模型进行器官分割,并通过OpenAI的GPT模型生成器官病变的详细描述。3D-MIR数据集旨在支持临床决策,通过提供精确的3D图像检索,帮助医生快速找到与特定病例相关的历史病
arXiv2023-11-23 更新310
住院患者诊疗数据集
本住院患者诊疗数据集以入院记录、出院小结、医嘱、检验、手术记录及治疗转归等全流程资料为基础,围绕住院诊疗 AI 研发与临床研究需求执行全流程标准化处理。 数据清洗环节建立全链路质控规则,剔除诊疗链路断裂、核心字段缺失、记录逻辑矛盾的无效样本;校验诊断编码、医嘱与检验结果、手术记录与转归信息的对应一致性,过滤重复记录与异常值,保障数据完整合规。 数据加工阶段执行全量隐私脱敏,通过标识符替换、敏感字段
贵州省数据知识产权登记平台2026-07-28 更新70
Data_Sheet_1_Development and Validation of a Novel Nomogram for Preoperative Prediction of In-Hospital Mortality After Coronary Artery Bypass Grafting Surgery in Heart Failure With Reduced Ejection Fraction.docx
Background and Aims: Patients with heart failure with reduced ejection fraction (HFrEF) are among the most challenging patients undergoing coronary artery bypass grafting surgery (CABG). Several surgi
NIAID Data Ecosystem60
A Learning-based Model to Evaluate Hospitalization Priority in COVID-19 Pandemics. ZHENG et al
The additional supplemental items show the list of eligible literatures that is retrieved from the World Health Organization COVID-19 database, the difference in clinical variables between severe and
Mendeley Data2020-07-28 更新60



