Using natural language processing of clinical text to enhance identification of opioid-related overdoses in electronic health records data
Using natural language processing of clinical text to enhance identification of opioid-related overdoses in electronic health records data
复制标题
DOI：
10.1002/pds.4810
复制
发表时间：
2019-08-01
影响因子：
2.6
通讯作者：
Coplan, Paul M.
中科院分区：
文献类型：
--
作者：
Hazlehurst, Brian;Green, Carla A.;Coplan, Paul M.
目的 增强自动化方法，使用电子健康记录 (EHR) 数据库准确识别阿片类药物相关过量用药并对过量类型进行分类。方法 我们开发了一种自然语言处理 (NLP) 软件应用程序，用于对用药过量的临床文本文档进行编码，包括识别自残意图、涉及的物质、药物滥用和药物使用错误。使用与疑似用药过量病例和用药过量风险较高的个人记录相平衡的数据集，我们使用 Kaiser Permanente Northwest 数据开发和验证了该应用程序，然后使用 Kaiser Permanente Washington 数据测试了该应用程序的可移植性。对数据集进行图表审查，为自动化方法的比较和评估提供黄金标准。结果 该方法在识别过量（敏感性 = 0.80，特异性 = 0.93）、故意过量（敏感性 = 0.81，特异性 = 0.98）以及涉及阿片类药物（不包括海洛因，敏感性 = 0.72，特异性 = 0.96）和海洛因（敏感性 = 0.84，特异性 = 1.0）方面表现良好。该方法在识别由于患者错误导致的药物不良反应和过量用药方面表现不佳，在识别与阿片类药物相关的无意过量用药中的药物滥用方面表现较好（敏感性 = 0.67，特异性 = 0.96）。对于上述许多分类，使用验证数据集进行的评估仅在特异性和阴性预测值方面产生了显着降低。然而，这些测量值仍保持在 0.80 以上，因此，开发期间观察到的性能在验证期间基本保持不变。在评估可移植性时获得了类似的结果，尽管由于数据库中缺少文本临床记录而导致无意过量用药的敏感性显着降低。结论 处理文本临床记录的方法有望提高使用 EHR 数据根据类型识别和分类过量用药的准确性和保真度。
Purpose To enhance automated methods for accurately identifying opioid-related overdoses and classifying types of overdose using electronic health record (EHR) databases. Methods We developed a natural language processing (NLP) software application to code clinical text documentation of overdose, including identification of intention for self-harm, substances involved, substance abuse, and error in medication usage. Using datasets balanced with cases of suspected overdose and records of individuals at elevated risk for overdose, we developed and validated the application using Kaiser Permanente Northwest data, then tested portability of the application using Kaiser Permanente Washington data. Datasets were chart-reviewed to provide a gold standard for comparison and evaluation of the automated method. Results The method performed well in identifying overdose (sensitivity = 0.80, specificity = 0.93), intentional overdose (sensitivity = 0.81, specificity = 0.98), and involvement of opioids (excluding heroin, sensitivity = 0.72, specificity = 0.96) and heroin (sensitivity = 0.84, specificity = 1.0). The method performed poorly at identifying adverse drug reactions and overdose due to patient error and fairly at identifying substance abuse in opioid-related unintentional overdose (sensitivity = 0.67, specificity = 0.96). Evaluation using validation datasets yielded significant reductions, in specificity and negative predictive values only, for many classifications mentioned above. However, these measures remained above 0.80, thus, performance observed during development was largely maintained during validation. Similar results were obtained when evaluating portability, although there was a significant reduction in sensitivity for unintentional overdose that was attributed to missing text clinical notes in the database. Conclusions Methods that process text clinical notes show promise for improving accuracy and fidelity at identifying and classifying overdoses according to type using EHR data.