arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.09599cs.CLcs.AIcs.SYeess.SPeess.SY
收藏

放射学文本分析系统(RadText)的体系结构与评价

Radiology Text Analysis System (RadText): Architecture and Evaluation

The University of Texas at Austin(德克萨斯大学奥斯汀分校);Weill Cornell Medicine(威尔康奈尔医学院);National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH)(美国国立卫生研究院国家医学图书馆国家生物技术信息中心)

Song Wang, Mingquan Lin, Ying Ding, George Shih, Zhiyong Lu, Yifan Peng

摘要:

分析放射学报告是一项耗时且容易出错的任务,这就需要一种高效的自动化放射学报告分析系统来减轻放射科医生的工作量并鼓励精确诊断。在这项工作中,我们介绍了RadText,一个由Python开发的开源放射学文本分析系统。RadText提供了一个易于使用的文本分析管道,包括去识别、分段、句子分割和单词标记化、命名实体识别、解析和否定检测。RadText采用灵活的模块化设计,提供混合文本处理模式,支持原始文本处理和本地处理,从而实现更好的可用性和更好的数据隐私。RadText采用BioC作为统一的接口,并将输入/输出转换为与观察性医学成果伙伴关系(OMOP)通用数据模型(CDM)兼容的结构化表示。这允许在多个不同的数据源中采用更系统的方法进行观察研究。我们在MIMIC-CXR数据集上评估了RadText,并为这项工作注释了五个新的疾病标签。RadText展示了高度准确的分类性能,平均精度为0.94,召回率为0.94,F-1得分为0.92。我们已经在https://github.com/bionlplab/radtext上提供了我们的代码、文档、示例和测试集。

英文摘要:

Analyzing radiology reports is a time-consuming and error-prone task, which raises the need for an efficient automated radiology report analysis system to alleviate the workloads of radiologists and encourage precise diagnosis. In this work, we present RadText, an open-source radiology text analysis system developed by Python. RadText offers an easy-to-use text analysis pipeline, including de-identification, section segmentation, sentence split and word tokenization, named entity recognition, parsing, and negation detection. RadText features a flexible modular design, provides a hybrid text processing schema, and supports raw text processing and local processing, which enables better usability and improved data privacy. RadText adopts BioC as the unified interface, and also standardizes the input / output into a structured representation compatible with Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM). This allows for a more systematic approach to observational research across multiple, disparate data sources. We evaluated RadText on the MIMIC-CXR dataset, with five new disease labels we annotated for this work. RadText demonstrates highly accurate classification performances, with an average precision of, a recall of 0.94, and an F-1 score of 0.92. We have made our code, documentation, examples, and the test set available at https://github.com/bionlplab/radtext .

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑