Moon Sungrim, Wu Yuqi, Doughty Jay B, Wieland Mark L, Philpot Lindsey M, Fan Jungwei W, Njeru Jane W
National Center for Advanced Translational Science, National Institutes of Health, Rockville, MD.
Department of Artificial Intelligence & Informatics, Mayo Clinic, Rochester, MN.
Mayo Clin Proc Digit Health. 2024 Sep;2(3):411-420. doi: 10.1016/j.mcpdig.2024.06.008. Epub 2024 Jul 8.
To develop natural language processing (NLP) solutions for identifying patients' unmet social needs to enable timely intervention.
Design: A retrospective cohort study with review and annotation of clinical notes to identify unmet social needs, followed by using the annotations to develop and evaluate NLP solutions.
A total of 1103 primary care patients seen at a large academic medical center from June 1, 2019, to May 31, 2021 and referred to a community health worker (CHW) program. Clinical notes and portal messages of 200 age and sex-stratified patients were sampled for annotation of unmet social needs.
Two NLP solutions were developed and compared. The first solution employed similarity-based classification on top of sentences represented as semantic embedding vectors. The second solution involved designing of terms and patterns for identifying each domain of unmet social needs in the clinical text.
Precision, recall, and f1-score of the NLP solutions.
A total of 5675 clinical notes and 475 portal messages were annotated, with an inter-annotator agreement of 0.938. The best NLP solution achieved an f1-score of 0.95 and was applied to the entire CHW-referred cohort (n=1103), of whom >80% had at least 1 unmet social need within the 6 months before the first CHW referral. Financial strain and health literacy were the top 2 domains of unmet social needs across most of the sex and age strata.
Clinical text contains rich information about patients' unmet social needs. The NLP can achieve good performance in identifying those needs for CHW referral and facilitate data-driven research on social determinants of health.
开发自然语言处理（NLP）解决方案，以识别患者未满足的社会需求，从而实现及时干预。
设计：一项回顾性队列研究，对临床记录进行审查和注释以识别未满足的社会需求，然后使用这些注释来开发和评估NLP解决方案。
2019年6月1日至2021年5月31日期间在一家大型学术医疗中心就诊并被转介至社区卫生工作者（CHW）项目的1103名初级保健患者。对200名按年龄和性别分层的患者的临床记录和门户消息进行抽样，以注释未满足的社会需求。
开发并比较了两种NLP解决方案。第一种解决方案在表示为语义嵌入向量的句子之上采用基于相似度的分类。第二种解决方案涉及设计用于识别临床文本中未满足社会需求的每个领域的术语和模式。
NLP解决方案的精确率、召回率和F1分数。
共注释了5675份临床记录和475条门户消息，注释者间一致性为0.938。最佳NLP解决方案的F1分数达到0.95，并应用于整个CHW转介队列（n = 1103），其中超过80%的患者在首次CHW转介前6个月内至少有1项未满足的社会需求。在大多数性别和年龄层中，经济压力和健康素养是未满足社会需求的前两大领域。
临床文本包含有关患者未满足社会需求的丰富信息。NLP在识别这些需求以进行CHW转介方面可取得良好表现，并有助于开展关于健康社会决定因素的数据驱动研究。
Zotero 插件
