利用自然语言处理技术改进基于电子健康记录结构化数据的手术部位感染监测。
Using Natural Language Processing to improve EHR Structured Data-based Surgical Site Infection Surveillance.
作者信息
Shi Jianlin, Liu Siru, Pruitt Liese C C, Luppens Carolyn L, Ferraro Jeffrey P, Gundlapalli Adi V, Chapman Wendy W, Bucher Brian T
机构信息
School of Medicine, University of Utah, Salt Lake City, Utah, US.
Intermountain Healthcare, Salt Lake City, Utah, US.
出版信息
AMIA Annu Symp Proc. 2020 Mar 4;2019:794-803. eCollection 2019.
Abstract
Surgical Site Infection surveillance in healthcare systems is labor intensive and plagued by underreporting as current methodology relies heavily on manual chart review. The rapid adoption of electronic health records (EHRs) has the potential to allow the secondary use of EHR data for quality surveillance programs. This study aims to investigate the effectiveness of integrating natural language processing (NLP) outputs with structured EHR data to build machine learning models for SSI identification using real-world clinical data. We examined a set of models using structured data with and without NLP document-level, mention-level, and keyword features. The top-performing model was based on a Random Forest classifier enhanced with NLP document-level features achieving a 0.58 sensitivity, 0.97 specificity, 0.54 PPV, 0.98 NPV, and 0.52 F score. We further interrogated the feature contributions, analyzed the errors, and discussed future directions.
摘要
医疗系统中的手术部位感染监测工作劳动强度大，且由于当前方法严重依赖人工病历审查，存在报告不足的问题。电子健康记录（EHR）的迅速采用有可能使EHR数据用于质量监测项目的二次利用。本研究旨在调查将自然语言处理（NLP）输出与结构化EHR数据相结合，以利用真实世界临床数据构建用于识别手术部位感染的机器学习模型的有效性。我们使用了一组包含和不包含NLP文档级、提及级和关键词特征的结构化数据的模型进行研究。表现最佳的模型基于一个通过NLP文档级特征增强的随机森林分类器，其灵敏度为0.58，特异度为0.97，阳性预测值为0.54，阴性预测值为0.98，F值为0.52。我们进一步探究了特征贡献，分析了误差，并讨论了未来的方向。
相似文献
1
Using Natural Language Processing to improve EHR Structured Data-based Surgical Site Infection Surveillance.利用自然语言处理技术改进基于电子健康记录结构化数据的手术部位感染监测。
AMIA Annu Symp Proc. 2020 Mar 4;2019:794-803. eCollection 2019.
2
Risk prediction using natural language processing of electronic mental health records in an inpatient forensic psychiatry setting.利用电子心理健康记录的自然语言处理进行住院法医精神病学环境中的风险预测。
J Biomed Inform. 2018 Oct;86:49-58. doi: 10.1016/j.jbi.2018.08.007. Epub 2018 Aug 14.
3
Automated feature selection of predictors in electronic medical records data.电子病历数据中预测指标的自动特征选择
Biometrics. 2019 Mar;75(1):268-277. doi: 10.1111/biom.12987. Epub 2019 Apr 2.
4
A comparison of word embeddings for the biomedical natural language processing.生物医学自然语言处理中词嵌入的比较。
J Biomed Inform. 2018 Nov;87:12-20. doi: 10.1016/j.jbi.2018.09.008. Epub 2018 Sep 12.
5
Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals.评估电子健康记录数据源及识别高血压个体的算法方法。
J Am Med Inform Assoc. 2017 Jan;24(1):162-171. doi: 10.1093/jamia/ocw071. Epub 2016 Aug 7.
6
Using Clinical Notes and Natural Language Processing for Automated HIV Risk Assessment.利用临床记录和自然语言处理进行自动化 HIV 风险评估。
J Acquir Immune Defic Syndr. 2018 Feb 1;77(2):160-166. doi: 10.1097/QAI.0000000000001580.
7
Identifying lupus patients in electronic health records: Development and validation of machine learning algorithms and application of rule-based algorithms.在电子健康记录中识别狼疮患者：机器学习算法的开发和验证以及基于规则算法的应用。
Semin Arthritis Rheum. 2019 Aug;49(1):84-90. doi: 10.1016/j.semarthrit.2019.01.002. Epub 2019 Jan 4.
8
A method for cohort selection of cardiovascular disease records from an electronic health record system.一种从电子健康记录系统中选择心血管疾病记录队列的方法。
Int J Med Inform. 2017 Jun;102:138-149. doi: 10.1016/j.ijmedinf.2017.03.015. Epub 2017 Mar 30.
9
Automated detection of substance use information from electronic health records for a pediatric population.从电子健康记录中自动检测儿科人群的物质使用信息。
J Am Med Inform Assoc. 2021 Sep 18;28(10):2116-2127. doi: 10.1093/jamia/ocab116.
10
Leveraging Natural Language Processing to Improve Electronic Health Record Suicide Risk Prediction for Veterans Health Administration Users.利用自然语言处理提高退伍军人健康管理局用户电子健康记录自杀风险预测
J Clin Psychiatry. 2023 Jun 19;84(4):22m14568. doi: 10.4088/JCP.22m14568.
引用本文的文献
1
Artificial intelligence in hospital infection prevention: an integrative review.医院感染预防中的人工智能：一项综合综述。
Front Public Health. 2025 Apr 2;13:1547450. doi: 10.3389/fpubh.2025.1547450. eCollection 2025.
2
Using natural language processing in emergency medicine health service research: A systematic review and meta-analysis.在急诊医学卫生服务研究中使用自然语言处理：一项系统评价和荟萃分析。
Acad Emerg Med. 2024 Jul;31(7):696-706. doi: 10.1111/acem.14937. Epub 2024 May 16.
3
An explainable long short-term memory network for surgical site infection identification.用于手术部位感染识别的可解释长短时记忆网络。
Surgery. 2024 Jul;176(1):24-31. doi: 10.1016/j.surg.2024.03.006. Epub 2024 Apr 18.
4
Venous Access: National Guideline and Registry Development (VANGUARD): Advancing Patient-Centered Venous Access Care Through the Development of a National Coordinated Registry Network.静脉通路：国家指南和注册库发展（VANGUARD）：通过建立国家协调的注册库网络，推进以患者为中心的静脉通路护理。
J Med Internet Res. 2023 Nov 24;25:e43658. doi: 10.2196/43658.
5
The augmented value of using clinical notes in semi-automated surveillance of deep surgical site infections after colorectal surgery.使用临床记录在结直肠手术后半自动化监测深部手术部位感染中的增值作用。
Antimicrob Resist Infect Control. 2023 Oct 26;12(1):117. doi: 10.1186/s13756-023-01316-x.
6
Developing an LSTM Model to Identify Surgical Site Infections using Electronic Healthcare Records.使用电子健康记录开发长短期记忆模型以识别手术部位感染
AMIA Jt Summits Transl Sci Proc. 2023 Jun 16;2023:330-339. eCollection 2023.
7
Performance of machine learning algorithms for surgical site infection case detection and prediction: A systematic review and meta-analysis.用于手术部位感染病例检测和预测的机器学习算法性能：系统评价与荟萃分析。
Ann Med Surg (Lond). 2022 Nov 23;84:104956. doi: 10.1016/j.amsu.2022.104956. eCollection 2022 Dec.
8
Machine learning approaches for electronic health records phenotyping: a methodical review.基于机器学习的电子健康记录表型分析方法：系统评价
J Am Med Inform Assoc. 2023 Jan 18;30(2):367-381. doi: 10.1093/jamia/ocac216.
9
Standard Vocabularies to Improve Machine Learning Model Transferability With Electronic Health Record Data: Retrospective Cohort Study Using Health Care-Associated Infection.利用电子健康记录数据提高机器学习模型可转移性的标准词汇表：使用医疗相关感染的回顾性队列研究
JMIR Med Inform. 2022 Aug 30;10(8):e39057. doi: 10.2196/39057.
10
A Deep Learning Approach to Estimate the Incidence of Infectious Disease Cases for Routinely Collected Ambulatory Records: The Example of Varicella-Zoster.深度学习方法估算常规收集的门诊记录中传染病病例的发生率：以水痘-带状疱疹为例。
Int J Environ Res Public Health. 2022 May 13;19(10):5959. doi: 10.3390/ijerph19105959.
本文引用的文献
1
Trie-based rule processing for clinical NLP: A use-case study of n-trie, making the ConText algorithm more efficient and scalable.基于 Trie 的规则处理在临床自然语言处理中的应用：n-trie 的使用案例研究，使 ConText 算法更高效、更具可扩展性。
J Biomed Inform. 2018 Sep;85:106-113. doi: 10.1016/j.jbi.2018.08.002. Epub 2018 Aug 6.
2
Identifying surgical site infections in electronic health data using predictive models.使用预测模型识别电子健康数据中的手术部位感染。
J Am Med Inform Assoc. 2018 Sep 1;25(9):1160-1166. doi: 10.1093/jamia/ocy075.
3
Accelerating Chart Review Using Automated Methods on Electronic Health Record Data for Postoperative Complications.利用电子健康记录数据的自动化方法加速术后并发症的图表审查。
AMIA Annu Symp Proc. 2017 Feb 10;2016:1822-1831. eCollection 2016.
4
American College of Surgeons and Surgical Infection Society: Surgical Site Infection Guidelines, 2016 Update.美国外科医师学会和外科感染学会：《手术部位感染指南，2016年更新》
J Am Coll Surg. 2017 Jan;224(1):59-74. doi: 10.1016/j.jamcollsurg.2016.10.029. Epub 2016 Nov 30.
5
Knowledge Author: facilitating user-driven, domain content development to support clinical information extraction.知识作者：促进用户驱动的领域内容开发，以支持临床信息提取。
J Biomed Semantics. 2016 Jun 23;7(1):42. doi: 10.1186/s13326-016-0086-9.
6
Underlying reasons associated with hospital readmission following surgery in the United States.美国术后再次住院的潜在原因。
JAMA. 2015 Feb 3;313(5):483-95. doi: 10.1001/jama.2014.18614.
7
A comparison of 2 surgical site infection monitoring systems.两种手术部位感染监测系统的比较。
JAMA Surg. 2015 Jan;150(1):51-7. doi: 10.1001/jamasurg.2014.2891.
8
HITECH spurs EHR vendor competition and innovation, resulting in increased adoption.《健康信息技术经济与临床健康法案》刺激了电子健康记录供应商的竞争与创新，从而提高了其采用率。
Am J Manag Care. 2014 Sep;20(9):734-40.
9
From research to nationwide implementation: the impact of AHRQ's HAI prevention program.从研究到全国范围实施：AHRQ 的 HAI 预防计划的影响。
Med Care. 2014 Feb;52(2 Suppl 1):S91-6. doi: 10.1097/MLR.0000000000000037.
10
Exploring the frontier of electronic health record surveillance: the case of postoperative complications.探索电子健康记录监测的前沿：以术后并发症为例。
Med Care. 2013 Jun;51(6):509-16. doi: 10.1097/MLR.0b013e31828d1210.
Zotero 插件