Department of Medical Informatics, Osaka University Graduate School of Medicine, Suita, Osaka, Japan; National Institute of Information and Communications Technology, Seika, Kyoto, Japan.
Department of Medical Informatics, Osaka University Graduate School of Medicine, Suita, Osaka, Japan.
J Biomed Inform. 2021 Apr;116:103729. doi: 10.1016/j.jbi.2021.103729. Epub 2021 Mar 9.
Extracting clinical terms from free-text format radiology reports is a first important step toward their secondary use. However, there is no general consensus on the kind of terms to be extracted. In this paper, we propose an information model comprising three types of clinical entities: observations, clinical findings, and modifiers. Furthermore, to determine its applicability for in-house radiology reports, we extracted clinical terms with state-of-the-art deep learning models and compared the results. We trained and evaluated models using 540 in-house chest computed tomography (CT) reports annotated by multiple medical experts. Two deep learning models were compared, and the effect of pre-training was explored. To investigate the generalizability of the model, we evaluated the use of other institutional chest CT reports. The micro F1-score of our best performance model using in-house and external datasets were 95.36% and 94.62%, respectively. Our results indicated that entities defined in our information model were suitable for extracting clinical terms from radiology reports, and the model was sufficiently generalizable to be used with dataset from other institutions.
从自由文本格式的放射学报告中提取临床术语是对其进行二次利用的首要步骤。然而，对于要提取的术语类型，目前尚无普遍共识。在本文中，我们提出了一个信息模型，其中包含三种类型的临床实体：观察结果、临床发现和修饰符。此外，为了确定其在内部放射学报告中的适用性，我们使用最先进的深度学习模型提取了临床术语，并对结果进行了比较。我们使用 540 份由多名医学专家注释的内部胸部计算机断层扫描（CT）报告进行了培训和评估。比较了两种深度学习模型，并探讨了预训练的效果。为了研究模型的泛化能力，我们评估了使用其他机构胸部 CT 报告的情况。使用内部和外部数据集的最佳性能模型的微 F1 得分分别为 95.36%和 94.62%。我们的结果表明，我们的信息模型中定义的实体适用于从放射学报告中提取临床术语，并且该模型具有足够的通用性，可以与来自其他机构的数据集一起使用。
