A Topic Model and Visualization for Automatic Summarization of Patient Records

用于自动汇总患者记录的主题模型和可视化

基本信息

批准号：
8919947
负责人：
Corey Wells Arnold
金额：
$ 16.11万
依托单位：
UNIVERSITY OF CALIFORNIA LOS ANGELES
依托单位国家：
美国
项目类别：
财政年份：
2014
资助国家：
美国
起止时间：
2014-09-01 至 2017-08-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/8919947
关键词：
Area Beds Caring Cirrhosis Clinical Clinical Data Clinical Medicine Code Cognitive Complex Consult Data Data Collection Data Set Development Diagnosis Diagnostic tests Eating Encapsulated Ensure Environment Event Foundations Future Goals Health Health Personnel Imagery Individual Internet Intervention Lead Learning Liver Liver Cirrhosis Manuals Maps Markov chain Monte Carlo methodology Measures Medical Medical Errors Medical History Medical Records Methods Modeling Myocardial Infarction Obstruction Online Systems Outcome Patient Care Patients Physicians Primary Care Physician Process Provider Recording of previous events Records Reporting Research Research Proposals Resources Retrieval Source Specific qualifier value Structure Symptoms System Techniques Testing Text Time Weight Work base case-based discrete data expedited review improved innovation malignant breast neoplasm model design novel patient population trend

项目摘要

DESCRIPTION (provided by applicant): Primary care physicians (PCPs) are responsible for reviewing and understanding a wide spectrum of a patient's medical history in order to make informed decisions regarding care. However, a variety of factors impede this process, including: the increasing complexity and number of diagnostic tests and treatments, health information exchange standards that may add more information to the medical record, and the need to efficiently see more patients in less time. These obstructions can lead to an inhibition of dialogue between patients and providers, and possibly even medical errors. New methods are required to help expedite a healthcare provider's understanding of a patient's medical history, summarizing key information. The use of topic models for summarizing large, unstructured data collections is a growing area of research. However, to date little work has been done on adapting these models to the clinical reporting environment. This proposal seeks to develop a topic model and ensuing visualization system for automatically summarizing medical records to support PCPs. Two specific aims guide the proposed work: 1) to create a topic model of free-text clinical documents that integrates contextual patient- and document-level data, and discovers multi-word concepts; and 2) to utilize the proposed model to drive a web application that includes concept-, source-, and time-oriented views for automatically summarizing patient records. The proposed model's innovation is that it is uniquely adapted to clinical records by the incorporation of demographic and discrete data (e.g., lab results), which influences the discovery of topics in documents and allows for adaptation to each patient's specific history. As a test bed for this project, we will gather medical records coded with myocardial infarction (MI), breast cancer, or liver cirrhosis, as these patients will span a spectrum of clinical complexity. We estimate that 68,539 patient records will be included in this study. The developed topic model will be integrated into a web-based visualization that displays clinically pertinent topics over time, as well as other relevant clinical data. This visualization will be evaluated by PCPs to gauge its utility to support the review of medical histories. This R21 proposal breaks new ground in the use of topic models for clinical data, and will provide future avenues of research in new applications of the proposed model.

描述（由申请人提供）：初级保健医师（PCP）负责审查和了解患者病史的广泛范围，以便对护理做出明智的决定。但是，多种因素阻碍了这一过程，包括：诊断测试和治疗的复杂性和数量增加，健康信息交换标准可能会在病历中增加更多信息，并且需要在更少的时间内有效地看到更多患者。这些障碍会导致抑制患者和提供者之间的对话，甚至可能发生医疗错误。需要新的方法来帮助加快医疗保健提供者对患者病史的理解，从而总结关键信息。主题模型总结大型非结构化数据收集是一个越来越多的研究领域。但是，迄今为止，几乎没有完成将这些模型调整为临床报告环境的工作。该建议旨在开发主题模型和随后的可视化系统，以自动汇总医疗记录以支持PCP。两个具体的目标指导拟议的工作：1）创建一个自由文本临床文档的主题模型，该模型整合了上下文的患者和文档级数据，并发现多字概念； 2）利用所提出的模型来驱动包括概念，源和时间为导向的视图，以自动汇总患者记录。拟议的模型的创新是，该公司由Incormation独特地适应了临床记录人口统计和离散数据（例如，实验室结果），这会影响文档中的主题，并允许适应每个患者的特定病史。作为该项目的测试床，我们将收集用心肌梗塞（MI），乳腺癌或肝硬化的医疗记录，因为这些患者将跨越各种临床复杂性。我们估计本研究将包括68,539个患者记录。开发的主题模型将集成到基于Web的可视化中，该可视化随着时间的推移显示临床相关的主题以及其他相关的临床数据。 PCP将对此可视化进行评估，以衡量其实用性以支持对医学历史的审查。该R21提案在将主题模型用于临床数据方面打破了新的基础，并将在拟议模型的新应用中提供未来的研究途径。