Leveraging natural language processing to identify eligible lung cancer screening patients with the electronic health record.
Leveraging natural language processing to identify eligible lung cancer screening patients with the electronic health record.
复制标题
利用自然语言处理来识别具有电子健康记录的合格肺癌筛查患者。
DOI：
10.1016/j.ijmedinf.2023.105136
复制
发表时间：
2023
影响因子：
4.9
通讯作者：
Wright,Adam
中科院分区：
文献类型：
--
作者：
Liu,Siru;McCoy,AllisonB;Aldrich,MelindaC;Sandler,KimL;Reese,ThomasJ;Steitz,Bryan;Bian,Jiang;Wu,Yonghui;Russo,Elise;Wright,Adam
目的开发和验证一种方法，通过结合电子健康记录（EHR）中的结构化和非结构化吸烟数据来识别符合肺癌筛查（LCS）条件的患者。方法我们确定了年龄在50-80岁之间的患者，这些患者在2019年至2022年期间在范德比尔特大学医学中心（VUMC）的初级保健诊所至少有一次遭遇。我们微调了现有的自然语言处理（NLP）工具，使用从VUMC收集的临床笔记提取定量吸烟信息。然后，我们开发了一种方法，通过结合结构化数据和临床叙述的吸烟信息来识别符合LCS条件的患者。我们比较了这种方法与两种方法，以确定LCS资格只使用结构化EHR的吸烟信息。我们使用了50例有吸烟史的患者进行比较和验证。基于NLP的方法实现了0.909的F1分数和0.96的准确性。基线方法可以识别5，887名患者。与基线方法相比，使用所有结构化数据和基于NLP的算法确定的患者数量分别为7，194（22.2%）和10，231（73.8%）。NLP为基础的方法确定了589黑人/非洲裔美国人，显着增加了119%.ConclusionWe提出了一个可行的NLP为基础的方法来确定LCS合格的患者。它为临床决策支持工具的开发提供了技术基础，以潜在地提高LCS的利用率并减少医疗差异。
ObjectiveTo develop and validate an approach that identifies patients eligible for lung cancer screening (LCS) by combining structured and unstructured smoking data from the electronic health record (EHR).MethodsWe identified patients aged 50–80 years who had at least one encounter in a primary care clinic at Vanderbilt University Medical Center (VUMC) between 2019 and 2022. We fine-tuned an existing natural language processing (NLP) tool to extract quantitative smoking information using clinical notes collected from VUMC. Then, we developed an approach to identify patients who are eligible for LCS by combining smoking information from structured data and clinical narratives. We compared this method with two approaches to identify LCS eligibility only using smoking information from structured EHR. We used 50 patients with a documented history of tobacco use for comparison and validation.Results102,475 patients were included. The NLP-based approach achieved an F1-score of 0.909, and accuracy of 0.96. The baseline approach could identify 5,887 patients. Compared to the baseline approach, the number of identified patients using all structured data and the NLP-based algorithm was 7,194 (22.2 %) and 10,231 (73.8 %), respectively. The NLP-based approach identified 589 Black/African Americans, a significant increase of 119 %.ConclusionWe present a feasible NLP-based approach to identify LCS eligible patients. It provides a technical basis for the development of clinical decision support tools to potentially improve the utilization of LCS and diminish healthcare disparities.
DOI：
10.1109/ichi48887.2020.9374369
发表时间：
2020-11
期刊：
Proceedings. IEEE International Conference on Healthcare Informatics
影响因子：
--
作者：
Yang X;Yang H;Lyu T;Yang S;Guo Y;Bian J;Xu H;Wu Y
通讯作者：
Wu Y
美国预防服务工作组
影响因子：
--
作者：
Virginia Moyer;Kirsten Bibbins
通讯作者：
Kirsten Bibbins
影响因子：
254.7
作者：
Siegel, Rebecca L.;Miller, Kimberly D.;Jemal, Ahmedin
通讯作者：
Jemal, Ahmedin