Interactive machine learning methods for clinical natural language processing

用于临床自然语言处理的交互式机器学习方法

• 批准号: 8818096
• 负责人: HUA XU
• 金额: $ 55.84万
• 依托单位: UNIVERSITY OF TEXAS HLTH SCI CTR HOUSTON
• 依托单位国家: 美国
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-05-31 至 2018-09-28
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8818096
• 关键词: Abbreviations; Active Learning; Address; Adoption; Algorithms; Attention; Biomedical Research; Classification; Clinical; Clinical Data; Clinical Informatics; Clinical Research; Cognitive; Communities; Data; Data Set; Development; Disease; Educational workshop; Electronic Health Record; Face; Goals; Grant; Human; Hybrids; Knowledge; Label; Learning; Linguistics; Machine Learning; Manuals; Medical; Methodology; Methods; Modeling; Names; Natural Language Processing; Patients; Pattern; Performance; Pharmaceutical Preparations; Physicians; Process; Research; Research Personnel; Research Priority; Resources; Sampling; Solutions; Source; Specific qualifier value; Statistical Methods; Statistical Models; System; Technology; Testing; Text; Time; United States National Library of Medicine; base; clinical application; clinical phenotype; cohort; computer human interaction; computerized; cost; experience; improved; model development; novel; open source; statistics; success; tool; usability

DESCRIPTION (provided by applicant): Growing deployments of electronic health records (EHRs) systems have made massive clinical data available electronically. However, much of detailed clinical information of patients is embedded in narrative text and is not directly accessible for computerized clinical applications. Therefore, natural language processing (NLP) technologies, which can unlock information in narrative document, have received great attention in the medical domain. Current state-of-the-art NLP approaches often involve building probabilistic models. However, the wide adoption of statistical methods in clinical NLP faces two grand challenges: 1) the lack of large annotated clinical corpora; and 2) the lack of methodologies that can efficiently integrate linguistic and domain knowledge with statistical learning. High-performance statistical NLP methods rely on large scale and high quality annotations of clinical text, but it is time-consuming and costly to create large annotated clinica corpora as it often requires manual review by physicians. Moreover, the medical domain is knowledge intensive. To achieve optimal performance, probabilistic models need to leverage medical domain knowledge. Therefore, methods that can efficiently integrate domain and expert knowledge with machine learning processes to quickly build high-quality probabilistic models with minimum annotation cost would be highly desirable for clinical text processing. In this study, we propose to investigate interactive machine learning (IML) methods to address the above challenges in clinical NLP. An IML system builds a classification model in an iterative process, which can actively select informative samples for annotation based on models built on previously annotated samples, thus reducing the annotation cost for model development. More importantly, an IML system also involves human inputs to the learning process (e.g., an expert can specify important features for a classification task based on domain knowledge). Thus, IML is an ideal framework for efficiently integrating rule-based (via domain experts specifying features) and statistics-based (via different learning algorithms) approaches to clinical NLP. To achieve our goal, we propose three specific aims. In Aim 1, we plan to investigate different aspects of IML for word sense disambiguation, including developing new active learning algorithms and conducting cognitive usability analysis for efficient feature annotation by users. To demonstrate the broad uses of IML, we further extend IML approaches to two other important clinical NLP classification tasks: named entity recognition and clinical phenoytping in Aim 2. Finally we propose to disseminate the IML methods and tools to the biomedical research community in Aim 3.

描述(由申请人提供)：电子健康记录(EHR)系统的不断部署使大量临床数据可以电子化。然而，许多患者的详细临床信息嵌入到叙述性文本中，不能直接用于计算机化的临床应用。因此，能够解锁叙事性文档中信息的自然语言处理技术在医学领域受到了极大的关注。当前最先进的NLP方法通常涉及构建概率模型。然而，统计方法在临床NLP中的广泛采用面临着两大挑战：1)缺乏大型的标注临床语料库；2)缺乏能够有效地将语言和领域知识与统计学习相结合的方法。高性能的统计NLP方法依赖于大规模和高质量的临床文本标注，但创建大型标注的Clinica语料库既耗时又昂贵，因为它经常需要医生手动审查。此外，医学领域是知识密集型的。为了实现最佳性能，概率模型需要利用医学领域知识。因此，能够有效地将领域知识和专家知识与机器学习过程相结合，以最小的标注代价快速构建高质量的概率模型的方法将非常适合于临床文本处理。 在这项研究中，我们建议研究交互式机器学习(IML)方法来解决临床NLP中的上述挑战。IML系统在迭代过程中建立分类模型，它可以根据先前标注的样本建立的模型来主动选择信息丰富的样本进行标注，从而降低了模型开发的标注成本。更重要的是，IML系统还涉及对学习过程的人工输入(例如，专家可以基于领域知识为分类任务指定重要特征)。因此，IML是将基于规则(通过领域专家指定特征)和基于统计(通过不同的学习算法)的方法有效地集成到临床NLP的理想框架。为了实现我们的目标，我们提出了三个具体目标。在目标1中，我们计划研究IML用于词义消歧的不同方面，包括开发新的主动学习算法和进行认知可用性分析，以便用户有效地进行特征标注。为了展示IML的广泛应用，我们进一步将IML方法扩展到目标2中的另外两个重要的临床NLP分类任务：命名实体识别和临床表型识别。最后，我们建议在目标3中向生物医学研究社区传播IML方法和工具。