2022年-2025年住院及手术病历数据集

该数据为广州中惠医疗科技有限公司（已签订协议）在向医生等专业人士提供“iMDT管理平台”服务过程中经标识化处理后产生的临床病历数据，包含：临床诊断信息、临床肿瘤分期信息、入院记录、出院记录、手术记录具体信息。该数据已授权给广州中康数字科技有限公司，可用于医疗领域大模型微调、训练，或用于临床科研回顾性研究。
该数据基于图像、视频、文档等数据开发形成，具备病历文书数据结构规范化、标准化特征，可助力临床领域研究或支撑AI医疗模型开发。

This dataset comprises de-identified clinical medical record data generated by Guangzhou Zhonghui Medical Technology Co., Ltd. (which has signed relevant cooperation agreements) during the provision of the "iMDT Management Platform" service to medical professionals including doctors. The dataset includes clinical diagnosis information, clinical tumor staging information, admission records, discharge records, and detailed surgical record information. This dataset has been authorized to Guangzhou Zhongkang Digital Technology Co., Ltd. for fine-tuning and training of large language models (LLMs) in the healthcare domain, as well as for retrospective clinical scientific research. Developed from multi-modal data including images, videos, and documents, this dataset features standardized and normalized data structures for medical record documentation, which can facilitate clinical research and support the development of AI-powered medical models.

搜集汇总

背景与挑战

背景概述

该数据集包含广州中惠医疗提供的2012-2025年脱敏住院手术病历，涵盖诊断、分期、出入院及手术记录等结构化数据，已授权用于医疗AI训练和临床研究。数据具备标准化特征，支持多模态医疗模型开发。