基于10年结构化CT影像报告自然语言处理的患者癌症转移模式
回顾性纵向研究纳入2009年7月至2019年4月符合结构化模板的连续CT检查患者91665例(女性46939例,平均年龄61岁±15),手动标注2219份报告开发三个NLP模型(80%-20%训练/测试),另用448份手动标注报告验证。最佳NLP模型各器官准确率90%-99%,转移最常见于腹盆腔淋巴结(23.6%)、胸部淋巴结(17.6%)、肺(14.7%)、肝(13.7%)、骨(9.9%);前列腺癌和乳腺癌最常见首发转移部位为骨,胰腺癌和结直肠癌为肝。
要点
- 最佳NLP模型从CT报告识别转移的准确率各器官达90%-99%,验证集为448份手动标注报告。
- 全队列387359份报告显示转移最常见于腹盆腔淋巴结(23.6%)和胸部淋巴结(17.6%),其次为肺(14.7%)、肝(13.7%)、骨(9.9%)。
- 前列腺癌和乳腺癌最常见首发转移部位为骨,胰腺癌和结直肠癌为肝,提示不同癌种转移趋向性不同。
核心结论
- 自然语言处理可应用于癌症患者CT报告,生成大规模转移表型数据库,该数据库可与基因组研究结合,用于探索与治疗计划相关的预后影像表型。
研究设计与样本
- 回顾性纵向研究,纳入2009年7月至2019年4月连续CT检查且报告遵循科室结构化模板的患者91665例(女性46939例,平均年龄61岁±15),共标记387359份报告;三位放射科医生手动标注2219份报告(按80%-20%分割训练集和测试集)开发三个NLP模型,另用448份手动标注报告验证。
诊断标准与关键数值
- 最佳NLP模型在所有器官的准确率为90%至99%,各器官分别以准确率、精确率和召回率评估。
临床应用与阅片要点
- 本研究采用自然语言处理从结构化CT报告中提取转移信息,最佳模型各器官准确率达90%-99%,可用于构建大规模转移表型数据库。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Background Patterns of metastasis in cancer are increasingly relevant to prognostication and treatment planning but have historically been documented by means of autopsy series. Purpose To show the feasibility of using natural language processing (NLP) to gather accurate data from radiology reports for assessing spatial and temporal patterns of metastatic spread in a large patient cohort. Materials and Methods In this retrospective longitudinal study, consecutive patients who underwent CT from July 2009 to April 2019 and whose CT reports followed a departmental structured template were included. Three radiologists manually curated a sample of 2219 reports for the presence or absence of metastases across 13 organs; these manually curated reports were used to develop three NLP models with an 80%-20% split for training and test sets. A separate random sample of 448 manually curated reports was used for validation. Model performance was measured by accuracy, precision, and recall for each organ. The best-performing NLP model was used to generate a final database of metastatic disease across all patients. For each cancer type, statistical descriptive reports were provided by analyzing the frequencies of metastatic disease at the report and patient levels. Results In 91 665 patients (mean age ± standard deviation, 61 years ± 15; 46 939 women), 387 359 reports were labeled. The best-performing NLP model achieved accuracies from 90% to 99% across all organs. Metastases were most frequently reported in abdominopelvic (23.6% of all reports) and thoracic (17.6%) nodes, followed by lungs (14.7%), liver (13.7%), and bones (9.9%). Metastatic disease tropism is distinct among common cancers, with the most common first site being bones in prostate and breast cancers and liver among pancreatic and colorectal cancers. Conclusion Natural language processing may be applied to cancer patients' CT reports to generate a large database of metastatic phenotypes. Such a database could be combined with genomic studies and used to explore prognostic imaging phenotypes with relevance to treatment planning. © RSNA, 2021 Online supplemental material is available for this article.
引用
- Do RKG, Lupton K, Causa Andrieu PI, et al. Patterns of Metastatic Disease in Patients with Cancer Derived from Natural Language Processing of Structured CT Radiology Reports over a 10-year Period. Radiology. 2021. PMID: 34342503. doi:10.1148/radiol.2021210043
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。