DE-IDENTIFICATION OF FREE TEXT PROGRESS NOTES IN MEDICAL RECORDS

这个子项目是利用由NIH/NCRR资助的中心拨款提供的资源的许多研究子项目之一。子项目和调查员(PI)可能从另一个NIH来源获得了主要资金，因此可能会出现在其他CRISE条目中。列出的机构是针对中心的，而不一定是针对调查员的机构。根据HIPAA制定的指导方针，必须从患者的医疗记录中删除所有个人身份信息，然后才能与其他医学研究人员共享这些记录。我们正在开发算法，以识别自由文本护理笔记以及执行相同任务的临床医生。正在创建一个由受雇临床医生手动识别的护理笔记数据库，该数据库将公开提供，用于测试和评价识别算法。我们还在收集有关人类识别器性能的统计数据。我们将使用这些统计数据来测试我们的去身份算法是否至少和人类一样好

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. The subproject and investigator (PI) may have received primary funding from another NIH source, and thus could be represented in other CRISP entries. The institution listed is for the Center, which is not necessarily the institution for the investigator. According to the guidelines established by HIPAA, all personally identifiable information must be removed from patients' medical records before those records can be shared with other medical researchers. We are developing algorithms that will de-identify free-text nursing notes as well as clincians doing the same task. A database of nursing notes manually de-identifed by hired clinicians is being created that will be made publicly available for the testing and evaluation of de-identification algorithms. We are also gathering statistics about the performance of human de-identifiers. We will use those statistics to test whether our de-identification algorithms perform at least as well as human