DE-SynPUF
收藏arXiv2025-09-30 收录
下载链接：
https://www.cms.gov/Research-Statistics-Data-and-Systems/Downloadable-Public-Use-Files/SynPUFs/DE_Syn_PUF.html
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是由CMS提供的公开数据集，包含了2008年至2010年三年的电子病历（EMR）数据，其中包括住院、门诊和承保档案，以及受益人概要文件。此外，该数据集中的诊断代码遵循ICD-9标准，涵盖了19个类别，并包含了4,677,706个近邻对。与NUH2012数据集相比，该数据集规模较大。其任务包括聚类分析和最近邻搜索。
This dataset is a public dataset provided by CMS, containing three years of electronic medical record (EMR) data from 2008 to 2010. It includes inpatient, outpatient, and underwriting records, as well as beneficiary profiles. Additionally, the diagnostic codes in this dataset follow the ICD-9 standard, covering 19 categories and containing 4,677,706 nearest neighbor pairs. Compared with the NUH2012 dataset, this dataset has a larger scale. Its applicable tasks include cluster analysis and nearest neighbor search.
提供机构：
Centers for Medicare and Medicaid Services (CMS)
搜集汇总
数据集介绍
以上内容由遇见数据集搜集并总结生成
