基于深度学习的日本放射学报告中骨转移患者的检测。
Deep learning-based detection of patients with bone metastasis from Japanese radiology reports.
机构信息
Department of Medical Physics and Engineering, Osaka University Graduate School of Medicine, 1-7 Yamadaoka, Suita-Shi, Osaka, Japan.
Department of Radiology, Kansai Medical University Graduate School of Medicine, 2-5-1 Shinmachi, Hirakata-Shi, Osaka, Japan.
出版信息
Jpn J Radiol. 2023 Aug;41(8):900-908. doi: 10.1007/s11604-023-01413-2. Epub 2023 Mar 29.
PURPOSE
Deep learning (DL) is a state-of-the-art technique for developing artificial intelligence in various domains and it improves the performance of natural language processing (NLP). Therefore, we aimed to develop a DL-based NLP model that classifies the status of bone metastasis (BM) in radiology reports to detect patients with BM.
MATERIALS AND METHODS
The DL-based NLP model was developed by training long short-term memory using 1,749 free-text radiology reports written in Japanese. We adopted five-fold cross-validation and used 200 reports for testing the five models. The accuracy, sensitivity, specificity, precision, and area under the receiver operating characteristics curve (AUROC) were used for the model evaluation.
RESULTS
The developed model demonstrated classification performance with mean ± standard deviation of 0.912 ± 0.012, 0.924 ± 0.029, 0.901 ± 0.014, 0.898 ± 0.012, and 0.968 ± 0.004 for accuracy, sensitivity, specificity, precision, and AUROC, respectively.
CONCLUSION
The proposed DL-based NLP model may help in the early and efficient detection of patients with BM.
目的
深度学习（DL）是一种在各个领域开发人工智能的最新技术，它提高了自然语言处理（NLP）的性能。因此，我们旨在开发一种基于 DL 的 NLP 模型，该模型可以对放射学报告中的骨转移（BM）状态进行分类，以检测 BM 患者。
材料与方法
该基于 DL 的 NLP 模型是通过使用 1749 份用日语书写的免费文本放射学报告来训练长短期记忆（LSTM）而开发的。我们采用五折交叉验证，使用 200 份报告来测试 5 个模型。模型评估采用准确性、敏感度、特异性、精度和接收器操作特征曲线下的面积（AUROC）。
结果
所开发的模型表现出分类性能，平均值±标准偏差分别为 0.912±0.012、0.924±0.029、0.901±0.014、0.898±0.012 和 0.968±0.004，用于准确性、敏感度、特异性、精度和 AUROC。
结论
所提出的基于 DL 的 NLP 模型可能有助于早期和高效地检测 BM 患者。
Zotero 插件