自然语言处理放射学报告以检测缺血性卒中并发症
本研究训练机器学习分类器和规则系统,从CT/MRI放射学报告中识别水肿、中线移位、出血转化、脑实质血肿、脑室内出血及连续中线移位测量值。推导队列为550例急性大脑中动脉供血区缺血性卒中的2289份报告,并在另一机构及任意血管区域卒中患者报告上外部验证。BioClinicalBERT对所有二分类结局的AUPRC均最高:水肿>0.94、中线移位>0.98、出血转化>0.89、脑实质血肿>0.76。除脑实质血肿外,BioClinicalBERT优于lasso回归;针对脑室内出血的规则系统和连续中线移位测量分别优于BioClinicalBERT和线性回归。
要点
- BioClinicalBERT对水肿的AUPRC>0.94,中线移位>0.98,出血转化>0.89,脑实质血肿>0.76。
- BioClinicalBERT在所有结局上优于lasso回归(p<0.001),仅脑实质血肿无统计学差异(p=0.755)。
- 针对脑室内出血的规则系统优于BioClinicalBERT(p<0.001)。
- 针对连续中线移位测量的规则系统优于线性回归(p<0.001)。
- 模型在另一机构及任意血管区域卒中患者报告上外部验证,表现稳健。
适用人群与场景
- 推导队列:550例急性大脑中动脉供血区缺血性卒中患者的2289份CT/MRI报告。
- 外部验证:另一机构来源的报告及任意血管区域缺血性卒中患者的报告。
研究设计与关键结果
- 研究类型:自然语言处理模型开发与外部验证研究。
- 推导队列:550例急性大脑中动脉供血区缺血性卒中患者的2289份报告。
- BioClinicalBERT在全部数据集中对二分类预测的辨别性能最高:水肿AUPRC>0.94、中线移位AUPRC>0.98、出血转化AUPRC>0.89、脑实质血肿AUPRC>0.76。
- BioClinicalBERT在所有结局上优于lasso回归(p<0.001),但脑实质血肿除外(p=0.755)。
- 针对脑室内出血的规则系统优于BioClinicalBERT(p<0.001)。
- 针对连续中线移位测量的规则系统优于线性回归(p<0.001)。
证据类型、等级与局限
- 证据类型:自然语言处理模型开发与验证研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,医学定制的自然语言处理方法有多项重要大数据应用,包括可扩展的电子表型、增强临床风险预测模型以及促进医院环境中的自动警报系统。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: Abstraction of critical data from unstructured radiologic reports using natural language processing (NLP) is a powerful tool to automate the detection of important clinical features and enhance research efforts. We present a set of NLP approaches to identify critical findings in patients with acute ischemic stroke from radiology reports of computed tomography (CT) and magnetic resonance imaging (MRI).
METHODS: We trained machine learning classifiers to identify categorical outcomes of edema, midline shift (MLS), hemorrhagic transformation, and parenchymal hematoma, as well as rule-based systems (RBS) to identify intraventricular hemorrhage (IVH) and continuous MLS measurements within CT/MRI reports. Using a derivation cohort of 2289 reports from 550 individuals with acute middle cerebral artery territory ischemic strokes, we externally validated our models on reports from a separate institution as well as from patients with ischemic strokes in any vascular territory.
RESULTS: In all data sets, a deep neural network with pretrained biomedical word embeddings (BioClinicalBERT) achieved the highest discrimination performance for binary prediction of edema (area under precision recall curve [AUPRC] > 0.94), MLS (AUPRC > 0.98), hemorrhagic conversion (AUPRC > 0.89), and parenchymal hematoma (AUPRC > 0.76). BioClinicalBERT outperformed lasso regression (p < 0.001) for all outcomes except parenchymal hematoma (p = 0.755). Tailored RBS for IVH and continuous MLS outperformed BioClinicalBERT (p < 0.001) and linear regression, respectively (p < 0.001).
CONCLUSIONS: Our study demonstrates robust performance and external validity of a core NLP tool kit for identifying both categorical and continuous outcomes of ischemic stroke from unstructured radiographic text data. Medically tailored NLP methods have multiple important big data applications, including scalable electronic phenotyping, augmentation of clinical risk prediction models, and facilitation of automatic alert systems in the hospital setting.
参考来源
- Miller MI, Orfanoudaki A, Cronin M, et al. Natural Language Processing of Radiology Reports to Detect Complications of Ischemic Stroke. Neurocrit Care. 2022. PMID: 35534660. doi:10.1007/s12028-022-01513-3
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。