Yale School of Medicine, New Haven, Connecticut, USA.
Section of Digestive Diseases, Department of Medicine, Yale School of Medicine, New Haven, Connecticut, USA.
J Gastroenterol Hepatol. 2021 Jun;36(6):1590-1597. doi: 10.1111/jgh.15313. Epub 2021 Jan 25.
Guidelines recommend risk stratification scores in patients presenting with gastrointestinal bleeding (GIB), but such scores are uncommonly employed in practice. Automation and deployment of risk stratification scores in real time within electronic health records (EHRs) would overcome a major impediment. This requires an automated mechanism to accurately identify ("phenotype") patients with GIB at the time of presentation. The goal is to identify patients with acute GIB by developing and evaluating EHR-based phenotyping algorithms for emergency department (ED) patients.
We specified criteria using structured data elements to create rules for identifying patients and also developed multiple natural language processing (NLP)-based approaches for automated phenotyping of patients, tested them with tenfold cross-validation for 10 iterations (n = 7144) and external validation (n = 2988) and compared them with a standard method to identify patient conditions, the Systematized Nomenclature of Medicine. The gold standard for GIB diagnosis was the independent dual manual review of medical records. The primary outcome was the positive predictive value.
A decision rule using GIB-specific terms from ED triage and ED review-of-systems assessment performed better than the Systematized Nomenclature of Medicine on internal validation and external validation (positive predictive value = 85% confidence interval:83%-87% vs 69% confidence interval:66%-72%; P < 0.001). The syntax-based NLP algorithm and Bidirectional Encoder Representation from Transformers neural network-based NLP algorithm had similar performance to the structured-data fields decision rule.
An automated decision rule employing GIB-specific triage and review-of-systems terms can be used to trigger EHR-based deployment of risk stratification models to guide clinical decision making in real time for patients with acute GIB presenting to the ED.
指南建议对出现胃肠道出血 (GIB) 的患者进行风险分层评分，但此类评分在实践中并不常见。在电子健康记录 (EHR) 中实时自动化和部署风险分层评分将克服一个主要障碍。这需要一种自动机制来在就诊时准确识别 (“表型”) 出现 GIB 的患者。目标是通过开发和评估急诊科 (ED) 患者基于 EHR 的表型算法来识别急性 GIB 患者。
我们使用结构化数据元素指定标准，以创建用于识别患者的规则，还开发了多种基于自然语言处理 (NLP) 的方法来自动对患者进行表型分析，使用十折交叉验证进行了 10 次迭代 (n = 7144) 和外部验证 (n = 2988)，并与一种标准方法进行比较，该标准方法用于识别患者的病情，即医学系统命名法。GIB 诊断的金标准是对病历进行独立的双重手动审查。主要结局是阳性预测值。
使用 ED 分诊和 ED 系统评估中特定于 GIB 的术语的决策规则在内部验证和外部验证中的表现优于医学系统命名法 (阳性预测值=85%置信区间：83%-87% vs 69%置信区间：66%-72%；P<0.001)。基于语法的 NLP 算法和基于双向编码器表示的变压器神经网络 (Bidirectional Encoder Representation from Transformers neural network-based) NLP 算法的性能与结构化数据字段决策规则相似。
使用特定于 GIB 的分诊和系统评估术语的自动决策规则可用于触发基于 EHR 的风险分层模型的部署，以实时指导出现急性 GIB 的 ED 患者的临床决策。
