Lin Ching-Heng, Hsu Kai-Cheng, Liang Chih-Kuang, Lee Tsong-Hai, Shih Ching-Sen, Fann Yang C
Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Taoyuan 33305, Taiwan.
Bachelor Program in Artificial Intelligence, Chang Gung University, Taoyuan 33305, Taiwan.
Diagnostics (Basel). 2022 Aug 3;12(8):1882. doi: 10.3390/diagnostics12081882.
Patients with intracranial artery stenosis show high incidence of stroke. Angiography reports contain rich but underutilized information that can enable the detection of cerebrovascular diseases. This study evaluated various natural language processing (NLP) techniques to accurately identify eleven intracranial artery stenosis from angiography reports. Three NLP models, including a rule-based model, a recurrent neural network (RNN), and a contextualized language model, XLNet, were developed and evaluated by internal-external cross-validation. In this study, angiography reports from two independent medical centers (9614 for training and internal validation testing and 315 as external validation) were assessed. The internal testing results showed that XLNet had the best performance, with a receiver operating characteristic curve (AUROC) ranging from 0.97 to 0.99 using eleven targeted arteries. The rule-based model attained an AUROC from 0.92 to 0.96, and the RNN long short-term memory model attained an AUROC from 0.95 to 0.97. The study showed the potential application of NLP techniques such as the XLNet model for the routine and automatic screening of patients with high risk of intracranial artery stenosis using angiography reports. However, the NLP models were investigated based on relatively small sample sizes with very different report writing styles and a prevalence of stenosis case distributions, revealing challenges for model generalization.
颅内动脉狭窄患者的中风发生率很高。血管造影报告包含丰富但未充分利用的信息，这些信息可用于检测脑血管疾病。本研究评估了各种自然语言处理（NLP）技术，以从血管造影报告中准确识别出11种颅内动脉狭窄情况。开发了三种NLP模型，包括基于规则的模型、循环神经网络（RNN）和上下文语言模型XLNet，并通过内部-外部交叉验证进行评估。在本研究中，对来自两个独立医疗中心的血管造影报告（9614份用于训练和内部验证测试，315份用于外部验证）进行了评估。内部测试结果表明，XLNet表现最佳，使用11条目标动脉时，其受试者工作特征曲线（AUROC）范围为0.97至0.99。基于规则的模型的AUROC为0.92至0.96，RNN长短期记忆模型的AUROC为0.95至0.97。该研究表明，XLNet模型等NLP技术在使用血管造影报告对颅内动脉狭窄高危患者进行常规自动筛查方面具有潜在应用价值。然而，NLP模型是基于相对较小的样本量进行研究的，报告写作风格差异很大，狭窄病例分布也不均衡，这揭示了模型泛化面临的挑战。
