Pediatric Social History Annotation Corpus (PedSHAC)

PedSHAC是一个专门为儿科患者设计的新型标注语料库，由华盛顿大学医院系统的1260份临床笔记组成，专注于提取社会健康决定因素（SDoH）。该数据集通过事件基础的标注方案，捕捉了十个不同的健康决定因素，包括生活和经济稳定性、先前创伤、教育访问、物质使用历史和心理健康等。PedSHAC的创建旨在通过详细的SDoH标注，支持对儿童健康管理中SDoH角色的理解，并改善健康结果。该数据集的应用领域包括临床和研究环境，旨在解决SDoH信息在电子健康记录中的系统收集和利用问题。

PedSHAC is a novel annotated corpus specifically designed for pediatric patients, comprising 1,260 clinical notes from the University of Washington Hospital System, with a focus on extracting Social Determinants of Health (SDoH). Employing an event-based annotation schema, this corpus captures ten distinct health determinants, including life and economic stability, prior trauma, educational access, history of substance use, mental health, and others. The creation of PedSHAC aims to support understanding of the role of SDoH in pediatric healthcare management and improve health outcomes through detailed SDoH annotations. This corpus is applicable in both clinical and research settings, with the goal of addressing the systematic collection and utilization of SDoH information within electronic health records (EHRs).