基于机器学习的放射科报告自然语言处理在骨科创伤中的应用。
Machine learning based natural language processing of radiology reports in orthopaedic trauma.
机构信息
Department of Radiology, Treant Health Care Group, Dr. G.H. Amshoffweg 1, Hoogeveen, the Netherlands; Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, Groningen, the Netherlands.
Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Hanzeplein 1, Groningen, the Netherlands.
出版信息
Comput Methods Programs Biomed. 2021 Sep;208:106304. doi: 10.1016/j.cmpb.2021.106304. Epub 2021 Jul 23.
OBJECTIVES
To compare different Machine Learning (ML) Natural Language Processing (NLP) methods to classify radiology reports in orthopaedic trauma for the presence of injuries. Assessing NLP performance is a prerequisite for downstream tasks and therefore of importance from a clinical perspective (avoiding missed injuries, quality check, insight in diagnostic yield) as well as from a research perspective (identification of patient cohorts, annotation of radiographs).
METHODS
Datasets of Dutch radiology reports of injured extremities (n = 2469, 33% fractures) and chest radiographs (n = 799, 20% pneumothorax) were collected in two different hospitals and labeled by radiologists and trauma surgeons for the presence or absence of injuries. NLP classification was applied and optimized by testing different preprocessing steps and different classifiers (Rule-based, ML, and Bidirectional Encoder Representations from Transformers (BERT)). Performance was assessed by F1-score, AUC, sensitivity, specificity and accuracy.
RESULTS
The deep learning based BERT model outperforms all other classification methods which were assessed. The model achieved an F1-score of (95 ± 2)% and accuracy of (96 ± 1)% on a dataset of simple reports (n= 2469), and an F1 of (83 ± 7)% with accuracy (93 ± 2)% on a dataset of complex reports (n= 799).
CONCLUSION
BERT NLP outperforms traditional ML and rule-base classifiers when applied to Dutch radiology reports in orthopaedic trauma.
目的
比较不同的机器学习（ML）自然语言处理（NLP）方法，以分类骨科创伤中的放射学报告是否存在损伤。评估 NLP 的性能是下游任务的前提，因此从临床角度（避免漏诊、质量检查、诊断效果的了解）和研究角度（确定患者队列、放射照片注释）都很重要。
方法
收集了荷兰两家医院受伤四肢（n=2469，33%骨折）和胸部 X 光片（n=799，20%气胸）的放射学报告数据集，并由放射科医生和创伤外科医生对损伤的存在或不存在进行标记。通过测试不同的预处理步骤和不同的分类器（基于规则、ML 和双向编码器表示从变压器（BERT）），应用和优化了 NLP 分类。通过 F1 分数、AUC、敏感性、特异性和准确性来评估性能。
结果
基于深度学习的 BERT 模型优于评估的所有其他分类方法。该模型在简单报告数据集（n=2469）上的 F1 评分为（95±2）%，准确率为（96±1）%，在复杂报告数据集（n=799）上的 F1 评分为（83±7）%，准确率为（93±2）%。
结论
当应用于荷兰骨科创伤放射学报告时，BERT NLP 优于传统的 ML 和基于规则的分类器。
Zotero 插件