Rixe Nancy, Frisch Adam, Wang Zhendong, Martin Judith M, Suresh Srinivasan, Florin Todd A, Ramgopal Sriram
Division of Pediatric Emergency Medicine, UPMC Children's Hospital of Pittsburgh, University of Pittsburgh School of Medicine, Pittsburgh, PA, United States.
Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, PA, United States.
Front Digit Health. 2023 Feb 22;5:1104604. doi: 10.3389/fdgth.2023.1104604. eCollection 2023.
Chest radiographs are frequently used to diagnose community-acquired pneumonia (CAP) for children in the acute care setting. Natural language processing (NLP)-based tools may be incorporated into the electronic health record and combined with other clinical data to develop meaningful clinical decision support tools for this common pediatric infection. We sought to develop and internally validate NLP algorithms to identify pediatric chest radiograph (CXR) reports with pneumonia.
We performed a retrospective study of encounters for patients from six pediatric hospitals over a 3-year period. We utilized six NLP techniques: word embedding, support vector machines, extreme gradient boosting (XGBoost), light gradient boosting machines Naïve Bayes and logistic regression. We evaluated their performance of each model from a validation sample of 1,350 chest radiographs developed as a stratified random sample of 35% admitted and 65% discharged patients when both using expert consensus and diagnosis codes.
Of 172,662 encounters in the derivation sample, 15.6% had a discharge diagnosis of pneumonia in a primary or secondary position. The median patient age in the derivation sample was 3.7 years (interquartile range, 1.4-9.5 years). In the validation sample, 185/1350 (13.8%) and 205/1350 (15.3%) were classified as pneumonia by content experts and by diagnosis codes, respectively. Compared to content experts, Naïve Bayes had the highest sensitivity (93.5%) and XGBoost had the highest F1 score (72.4). Compared to a diagnosis code of pneumonia, the highest sensitivity was again with the Naïve Bayes (80.1%), and the highest F1 score was with the support vector machine (53.0%).
NLP algorithms can accurately identify pediatric pneumonia from radiography reports. Following external validation and implementation into the electronic health record, these algorithms can facilitate clinical decision support and inform large database research.
胸部X光片常用于急性护理环境中儿童社区获得性肺炎（CAP）的诊断。基于自然语言处理（NLP）的工具可整合到电子健康记录中，并与其他临床数据相结合，为这种常见的儿科感染开发有意义的临床决策支持工具。我们试图开发并在内部验证NLP算法，以识别患有肺炎的儿科胸部X光片（CXR）报告。
我们对6家儿科医院3年内患者的就诊情况进行了回顾性研究。我们运用了六种NLP技术：词嵌入、支持向量机、极端梯度提升（XGBoost）、轻量级梯度提升机、朴素贝叶斯和逻辑回归。当同时使用专家共识和诊断代码时，我们从1350张胸部X光片的验证样本（该样本为35%的住院患者和65%的出院患者的分层随机样本）中评估每个模型的性能。
在推导样本的172,662次就诊中，15.6%的患者主要或次要出院诊断为肺炎。推导样本中的患者年龄中位数为3.7岁（四分位间距为1.4 - 9.5岁）。在验证样本中，内容专家和诊断代码分别将185/1350（13.8%）和205/1350（15.3%）分类为肺炎。与内容专家相比，朴素贝叶斯的灵敏度最高（93.5%），XGBoost的F1分数最高（72.4）。与肺炎诊断代码相比，灵敏度最高的同样是朴素贝叶斯（80.1%），F1分数最高的是支持向量机（53.0%）。
NLP算法可以从X光片报告中准确识别儿科肺炎。经过外部验证并应用于电子健康记录后，这些算法可以促进临床决策支持并为大型数据库研究提供信息。
