Mining 100 million notes to find homelessness and adverse childhood experiences: 2 case studies of rare and severe social determinants of health in electronic health records
Mining 100 million notes to find homelessness and adverse childhood experiences: 2 case studies of rare and severe social determinants of health in electronic health records
复制标题
DOI：
10.1093/jamia/ocx059
复制
发表时间：
2018-01-01
影响因子：
6.4
通讯作者：
Denny, Joshua C.
中科院分区：
文献类型：
--
作者：
Bejan, Cosmin A.;Angiolillo, John;Denny, Joshua C.
了解如何从电子健康记录（EHR）中识别健康的社会决定因素可以为了解健康或疾病结果提供重要的见解。我们开发了一种方法，从一个大型的EHR库中捕获2种罕见而严重的健康社会决定因素，无家可归和不良童年经历（ACE）。我们采用word 2 vec和词汇联想挖掘无家可归相关的话。接下来，使用相关性反馈，我们从范德比尔特EHR中迭代搜索超过1亿条笔记来细化2个配置文件。七个评估员手动审查了排名靠前的结果2544患者访问相关的无家可归和1000例患者相关的ACE。word 2 vec产生了更好的性能（精确召回曲线下的面积[AUPRC]为0.94）比词汇协会（AUPRC = 0.83）提取无家可归相关的话。对这2种表型搜索的比较研究显示，无家可归者（AUPRC = 0.95）的搜索性能高于ACE（AUPRC = 0.79）。对无家可归人口的时间分析表明，大多数人长期无家可归。大多数ACE患者遭受性虐待（70%）和/或身体虐待（50.6%），排在首位的虐待者关键词是“父亲”（21.8%）和“母亲”（15.4%）。无家可归者的最常见的相关疾病是缺乏住房（62.8%）和烟草使用障碍（61.5%），而ACE患者是精神障碍（36.6%-47.6%）。我们提供了一个有效的解决方案，从EHR中挖掘无家可归和ACE信息，这可以促进这些健康的社会决定因素的大规模临床和遗传学研究。
Understanding how to identify the social determinants of health from electronic health records (EHRs) could provide important insights to understand health or disease outcomes. We developed a methodology to capture 2 rare and severe social determinants of health, homelessness and adverse childhood experiences (ACEs), from a large EHR repository.We first constructed lexicons to capture homelessness and ACE phenotypic profiles. We employed word2vec and lexical associations to mine homelessness-related words. Next, using relevance feedback, we refined the 2 profiles with iterative searches over 100 million notes from the Vanderbilt EHR. Seven assessors manually reviewed the top-ranked results of 2544 patient visits relevant for homelessness and 1000 patients relevant for ACE.word2vec yielded better performance (area under the precision-recall curve [AUPRC] of 0.94) than lexical associations (AUPRC = 0.83) for extracting homelessness-related words. A comparative study of searches for the 2 phenotypes revealed a higher performance achieved for homelessness (AUPRC = 0.95) than ACE (AUPRC = 0.79). A temporal analysis of the homeless population showed that the majority experienced chronic homelessness. Most ACE patients suffered sexual (70%) and/or physical (50.6%) abuse, with the top-ranked abuser keywords being "father" (21.8%) and "mother" (15.4%). Top prevalent associated conditions for homeless patients were lack of housing (62.8%) and tobacco use disorder (61.5%), while for ACE patients it was mental disorders (36.6%-47.6%).We provide an efficient solution for mining homelessness and ACE information from EHRs, which can facilitate large clinical and genetic studies of these social determinants of health.