Automated Extraction of Stroke Severity from Unstructured Electronic Health Records using Natural Language Processing.
Automated Extraction of Stroke Severity from Unstructured Electronic Health Records using Natural Language Processing.
复制标题
使用自然语言处理从非结构化电子健康记录中自动提取中风严重程度。
DOI：
10.1101/2024.03.08.24304011
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
Zafar,SaharF
中科院分区：
文献类型：
--
作者：
Fernandes,Marta;Westover,MBrandon;Singhal,AneeshB;Zafar,SaharF
多中心电子健康记录（EHR）可以支持中风护理的质量改进计划和比较有效性研究。然而，基于EHR的研究的局限性包括从大规模非结构化数据中提取关键临床变量的挑战。数据缺失使情况更加复杂。在这里，我们开发了一个自然语言处理（NLP）模型，自动读取EHR笔记，以确定NIH中风量表（NIHSS）评分的急性stroke. METHODS研究包括急性中风患者（>= 18岁）的笔记承认马萨诸塞州总医院（MGH）（2015-2022）。MGH数据分为训练集（70%）和保持测试集（30%）。建立了一个两阶段模型来预测入院NIHSS。在训练集中训练具有最小绝对收缩和选择算子（LASSO）的线性模型。对于记录了NIHSS的测试集中的注释，使用正则表达式提取评分（第1阶段），对于未记录NIHSS的注释，使用LASSO进行预测（第2阶段）。NIHSS的参考标准来自Get With The Guidelines Stroke Registry。两阶段模型在保持测试集上进行了测试，并在MIMIC-III数据集（重症监护医学信息市场-MIMIC III 2001-2012）v1中进行了验证。我们纳入了4，163名患者（MGH= 3，876; MIMIC= 287）;平均年龄为69岁[SD 15]; 53%为男性，72%为白色。90%的患者发生缺血性卒中，10%发生出血性卒中。两阶段模型的RMSE [95%CI]为3.13 [2.86-3.41]（SC= 0.90 [0.88-0. 91])结论基于NLP的自动模型可以从EHR中进行大规模的卒中严重程度表型分析，因此支持卒中的真实世界质量改进和比较有效性研究。
BACKGROUNDMulti-center electronic health records (EHR) can support quality improvement initiatives and comparative effectiveness research in stroke care. However, limitations of EHR-based research include challenges in abstracting key clinical variables from non-structured data at scale. This is further compounded by missing data. Here we develop a natural language processing (NLP) model that automatically reads EHR notes to determine the NIH stroke scale (NIHSS) score of patients with acute stroke.METHODSThe study included notes from acute stroke patients (>= 18 years) admitted to the Massachusetts General Hospital (MGH)(2015-2022). The MGH data were divided into training (70%) and hold-out test (30%) sets. A two-stage model was developed to predict the admission NIHSS. A linear model with the least absolute shrinkage and selection operator (LASSO) was trained within the training set. For notes in the test set where the NIHSS was documented, the scores were extracted using regular expressions (stage 1), for notes where NIHSS was not documented, LASSO was used for prediction (stage 2). The reference standard for NIHSS was obtained from Get With The Guidelines Stroke Registry. The two-stage model was tested on the hold-out test set and validated in the MIMIC-III dataset (Medical Information Mart for Intensive Care-MIMIC III 2001-2012) v1. 4, using root mean squared error (RMSE) and Spearman correlation (SC).RESULTSWe included 4,163 patients (MGH= 3,876; MIMIC= 287); average age of 69 [SD 15] years; 53% male, and 72% white. 90% patients had ischemic stroke and 10% hemorrhagic stroke. The two-stage model achieved a RMSE [95% CI] of 3.13 [2.86-3.41](SC= 0.90 [0.88-0. 91]) in the MGH hold-out test set and 2.01 [1.58-2.38](SC= 0.96 [0.94-0.97]) in the MIMIC validation set.CONCLUSIONSThe automatic NLP-based model can enable large-scale stroke severity phenotyping from EHR and therefore support real-world quality improvement and comparative effectiveness studies in stroke.