Electronic surveillance of patient safety events using natural language processing.

Electronic surveillance of patient safety events using natural language processing.
复制标题

DOI:
10.1177/14604582221132429
复制
发表时间:
2022-10
影响因子:
3
通讯作者:
Kimia, Amir A.
Kimia, Amir A.
中科院分区:
医学3区
文献类型:
--
作者:
Ozonoff, Al;Milliren, Carly E.;Fournier, Kerri;Welcher, Jennifer;Landschaft, Assaf;Samnaliev, Mihail;Saluvan, Mehmet;Waltzman, Mark;Kimia, Amir A.

文献摘要

参考文献

相似文献

我们描述了我们对医院数据(包括自由文本临床记录)中捕获的可报告安全性事件进行监测的方法。我们假设:a)一些患者安全性事件仅记录在临床记录中,而未记录在任何其他可访问的来源中;和B)从临床记录中大规模提取事件数据是可行的。我们使用正则表达式为机器学习模型生成训练数据集,并将该模型应用于全套临床记录,并进行进一步审查以识别感兴趣的安全事件。我们证明了这种方法对外周静脉(PIV)浸润和外渗(PIVIEs)。在第1阶段,我们收集了21,362份临床记录,其中2342份进行了审查。我们确定了125例PIV事件,其中44例(35%)未被其他患者安全系统捕获。在第2阶段,我们收集了60,735份临床记录,并确定了440起浸润事件。我们的分类器表现出90%以上的准确率。我们的方法,以确定安全事件的临床文件的自由文本提供了一个可行的和可扩展的方法,以加强现有的患者安全系统。专家评审员使用机器学习模型,可以对患者安全事件进行常规监测。
We describe our approach to surveillance of reportable safety events captured in hospital data including free-text clinical notes. We hypothesize that a) some patient safety events are documented only in the clinical notes and not in any other accessible source; and b) large-scale abstraction of event data from clinical notes is feasible. We use regular expressions to generate a training data set for a machine learning model and apply this model to the full set of clinical notes and conduct further review to identify safety events of interest. We demonstrate this approach on peripheral intravenous (PIV) infiltrations and extravasations (PIVIEs). During Phase 1, we collected 21,362 clinical notes, of which 2342 were reviewed. We identified 125 PIV events, of which 44 cases (35%) were not captured by other patient safety systems. During Phase 2, we collected 60,735 clinical notes and identified 440 infiltrate events. Our classifier demonstrated accuracy above 90%. Our method to identify safety events from the free text of clinical documentation offers a feasible and scalable approach to enhance existing patient safety systems. Expert reviewers, using a machine learning model, can conduct routine surveillance of patient safety events.
DOI: 10.1016/j.apnr.2011.06.002
发表时间: 2012-11-01
影响因子: 2.2
作者:
Collins, Sarah A.;Vawdrey, David K.
通讯作者: Vawdrey, David K.
DOI: 10.1542/peds.2018-0496
发表时间: 2019-02-01
期刊: PEDIATRICS
影响因子: 8
作者:
Hoffman, James M.;Keeling, Nicholas J.;Walsh, Kathleen E.
通讯作者: Walsh, Kathleen E.
DOI: 10.1136/bmjqs-2017-006975
发表时间: 2018-03-01
影响因子: 5.4
作者:
Bhise, Viraj;Sittig, Dean F.;Singh, Hardeep
通讯作者: Singh, Hardeep
DOI: 10.1056/nejm196301242680405
发表时间: 1963-01-01
影响因子: 158.5
作者:
LANGMUIR, AD
通讯作者: LANGMUIR, AD
DOI: 10.1016/s1070-3241(16)30180-8
发表时间: 1995-10-01
期刊: JOINT COMMISSION JOURNAL ON QUALITY IMPROVEMENT
影响因子: --
作者:
CULLEN, DJ;BATES, DW;LEAPE, LL
通讯作者: LEAPE, LL