Contextual Embeddings from Clinical Notes Improves Prediction of Sepsis
Contextual Embeddings from Clinical Notes Improves Prediction of Sepsis
复制标题
DOI：
10.1101/2021.03.02.21252779
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Fatemeh Amrollahi;S. Shashikumar;Fereshteh Razmi;S. Nemati
中科院分区：
文献类型：
--
作者：
Fatemeh Amrollahi;S. Shashikumar;Fereshteh Razmi;S. Nemati
败血症是一种危及生命的器官功能障碍，是一种由急性感染引发的临床综合征，每年影响超过100万美国人。未经治疗的败血症可发展为感染性休克和器官衰竭，使败血症成为医院发病率和死亡率的主要原因之一。众所周知，早期发现败血症和及时使用抗生素可以挽救生命。在这项工作中，我们使用深度学习方法设计了一种基于电子健康记录（EHR）数据的脓毒症预测算法。虽然大多数现有的基于ehr的败血症预测模型利用结构化数据，包括生命体征、实验室和临床信息，但我们表明，使用预训练的神经语言表示模型，结合基于临床文本的特征，允许合并非结构化数据，而无需明确需要基于本体的命名实体识别和分类。所提出的模型是在一个包含40000多名患者（包括2805名脓毒症患者）的大型重症监护数据库上进行训练的，并与竞争的基线模型进行比较。与仅基于结构化数据的基线模型相比，合并临床文献将AUC从0.81提高到0.84。我们的研究结果表明，通过预先训练的语言表示模型结合临床文本特征可以提高败血症的早期预测并减少误报。
Sepsis, a life-threatening organ dysfunction, is a clinical syndrome triggered by acute infection and affects over 1 million Americans every year. Untreated sepsis can progress to septic shock and organ failure, making sepsis one of the leading causes of morbidity and mortality in hospitals. Early detection of sepsis and timely antibiotics administration is known to save lives. In this work, we design a sepsis prediction algorithm based on data from electronic health records (EHR) using a deep learning approach. While most existing EHR-based sepsis prediction models utilize structured data including vitals, labs, and clinical information, we show that incorporation of features based on clinical texts, using a pre-trained neural language representation model, allows for incorporation of unstructured data without an explicit need for ontology-based named-entity recognition and classification. The proposed model is trained on a large critical care database of over 40,000 patients, including 2805 septic patients, and is compared against competing baseline models. In comparison to a baseline model based on structured data alone, incorporation of clinical texts improved AUC from 0.81 to 0.84. Our findings indicate that incorporation of clinical text features via a pre-trained language representation model can improve early prediction of sepsis and reduce false alarms.