ENACT网络正在利用开放健康自然语言处理工具包应对住房不稳定问题和无家可归者的情况。
The ENACT network is acting on housing instability and the unhoused using the open health natural language processing toolkit.
作者信息
Harris Daniel R, Fu Sunyang, Wen Andrew, Corbeau Alexandria, Henderson Darren, Hilsman Jordan, Oniani David, Wang Yanshan
机构信息
Center for Clinical and Translational Sciences, University of Kentucky, Lexington, KY, USA.
Institute for Biomedical Informatics, University of Kentucky, Lexington, KY, USA.
出版信息
J Clin Transl Sci. 2024 May 16;8(1):e98. doi: 10.1017/cts.2024.543. eCollection 2024.
Housing is an environmental social determinant of health that is linked to mortality and clinical outcomes. We developed a lexicon of housing-related concepts and rule-based natural language processing methods for identifying these housing-related concepts within clinical text. We piloted our methods on several test cohorts: a synthetic cohort generated by ChatGPT for initial infrastructure testing, a cohort with substance use disorders (SUD), and a cohort diagnosed with problems related to housing and economic circumstances (HEC). Our methods successfully identified housing concepts in our ChatGPT notes (recall = 1.0, precision = 1.0), our SUD population (recall = 0.9798, precision = 0.9898), and our HEC population (recall = N/A, precision = 0.9160).
住房是一种与死亡率和临床结果相关的健康环境社会决定因素。我们开发了一个与住房相关概念的词汇表和基于规则的自然语言处理方法，用于在临床文本中识别这些与住房相关的概念。我们在几个测试队列上对我们的方法进行了试点：一个由ChatGPT生成的合成队列用于初始基础设施测试，一个患有物质使用障碍（SUD）的队列，以及一个被诊断出与住房和经济状况（HEC）相关问题的队列。我们的方法在ChatGPT记录中成功识别出住房概念（召回率 = 1.0，精确率 = 1.0），在SUD人群中（召回率 = 0.9798，精确率 = 0.9898），以及在HEC人群中（召回率 = 无，精确率 = 0.9160）。
Zotero 插件