Derivation of a natural language processing algorithm to identify febrile infants.
Derivation of a natural language processing algorithm to identify febrile infants.
复制标题
推导自然语言处理算法来识别发热婴儿。
DOI：
10.1002/jhm.2732
复制
发表时间：
2022
影响因子：
2.6
通讯作者：
Gildea,Daniel
中科院分区：
文献类型：
--
作者：
Yaeger,JeffreyP;Lu,Jiahao;Jones,Jeremiah;Ertefaie,Ashkan;Fiscella,Kevin;Gildea,Daniel
背景诊断码可以对发热婴儿样本进行回顾性识别，但灵敏度较低，导致许多发热婴儿漏检。为了确保研究样本具有代表性，需要一种改进的方法。目的推导并内部验证一种自然语言处理算法，以识别发热婴儿，并将其性能与诊断代码进行比较。方法这项横断面研究包括 2016 年 1 月至 2017 年 12 月被带到儿科急诊科的 0-90 天婴儿。我们的目的是识别发烧婴儿，发烧的定义是记录的体温≥38°C。我们使用 2017 年的临床记录开发了两种基于规则的算法来识别发烧婴儿，并根据 2016 年的数据对其进行了测试。使用手动抽象作为黄金标准，我们使用接受者操作特征曲线下面积 (AUC)、灵敏度和特异性，将两种基于规则的算法（模型 1、2）与四个先前发布的诊断代码组（模型 5-8）的性能进行了比较。结果对于测试集（n= 1190）婴儿），184 名婴儿发烧（15.5%）。模型 1 和 2 的 AUC (0.92–0.95) 和敏感性 (86%–92%) 显着大于模型 5–8 (0.67–0.74; 20%–74%)，且具有相似的特异性 (93%–99%)。与模型 5-8 相比，模型 1 和 2 的样本表现出与金标准相似的特征，包括发烧患病率、中位年龄、细菌感染率、住院率和严重后果。结论研究结果表明，与诊断代码相比，基于规则的算法可以以更高的灵敏度准确识别发热婴儿，同时保留特异性。如果经过外部验证，基于规则的算法可能是创建代表性研究样本的重要工具，从而提高研究结果的普遍性。
BackgroundDiagnostic codes can retrospectively identify samples of febrile infants, but sensitivity is low, resulting in many febrile infants eluding detection. To ensure study samples are representative, an improved approach is needed.ObjectiveTo derive and internally validate a natural language processing algorithm to identify febrile infants and compare its performance to diagnostic codes.MethodsThis cross‐sectional study consisted of infants aged 0–90 days brought to one pediatric emergency department from January 2016 to December 2017. We aimed to identify infants with fever, defined as a documented temperature ≥38°C. We used 2017 clinical notes to develop two rule‐based algorithms to identify infants with fever and tested them on data from 2016. Using manual abstraction as the gold standard, we compared performance of the two rule‐based algorithms (Models 1, 2) to four previously published diagnostic code groups (Models 5–8) using area under the receiver‐operating characteristics curve (AUC), sensitivity, and specificity.ResultsFor the test set (n= 1190 infants), 184 infants were febrile (15.5%). The AUCs (0.92–0.95) and sensitivities (86%–92%) of Models 1 and 2 were significantly greater than Models 5–8 (0.67–0.74; 20%–74%) with similar specificities (93%–99%). In contrast to Models 5–8, samples from Models 1 and 2 demonstrated similar characteristics to the gold standard, including fever prevalence, median age, and rates of bacterial infections, hospitalizations, and severe outcomes.ConclusionsFindings suggest rule‐based algorithms can accurately identify febrile infants with greater sensitivity while preserving specificity compared to diagnostic codes. If externally validated, rule‐based algorithms may be important tools to create representative study samples, thereby improving generalizability of findings.