Targeted Neural Text Summarization of Electronic Medical Records to Improve Imaging Diagnostics

电子病历的定向神经文本摘要可改善影像诊断

• 批准号: 10443224
• 负责人: BYRON CASEY WALLACE
• 金额: $ 35.88万
• 依托单位: NORTHEASTERN UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-02 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10443224
• 关键词: Affect; Area; Automated Abstracting; Caring; Clinical; Cognitive; Complement; Computerized Medical Record; Consult; Data; Data Science; Decision Making; Diagnosis; Diagnostic; Diagnostic Errors; Diagnostic Imaging; Differential Diagnosis; Distant; Electronic Health Record; Feedback; Glean; Gold; Hospitals; Image; Lead; MRI Scans; Machine Learning; Measures; Medical; Medical History; Medical Imaging; Methods; Modeling; Modernization; Natural Language Processing; Output; Patients; Performance; Probability; Provider; Publishing; Radiology Specialty; Recording of previous events; Records; Reporting; Research; Retrieval; Running; Source; Specialist; Supervision; Surface; System; Text; Therapeutic; Thinking; Time; Training; Woman; Work; X-Ray Computed Tomography; accurate diagnosis; clinical center; clinical decision-making; clinical diagnostics; clinical practice; design; heuristics; impression; improved; insight; machine learning model; medical specialties; multimodality; natural language; novel; point of care; prototype; radiologist; recruit; relating to nervous system; unstructured data

Project Summary Targeted Neural Text Summarization of Electronic Medical Records to Improve Imaging Diagnosis Electronic health records (EHRs) contain a wealth of patient information that might inform diagnostic and therapeutic decision-making. However, much of this information is unstructured (i.e., free-text). This makes it difficult to find the few relevant notes that might inform a given decision amongst lengthy patient records, in turn rendering key information buried within EHR practically inaccessible to domain experts operating under time constraints. Consequently, clinical decisions are often made without the benefit of all available data. We propose to design, train, and deploy novel natural language processing (NLP) models that provide extractive summaries of the free-text data within EHR conditioned on particular queries; the intent is for such models to aid diagnosis and decision-making. We also propose to use these models to try and counteract the cognitive biases that domain experts bring to clinical practice. We focus specifically on the important and illustrative area of radiology, although the approach will generalize to other specialties. Radiologists performing imaging diagnosis do not have adequate time to carefully read through patient histories stored within EHR; they must instead make do with limited background information when interpreting imaging. We will build on our preliminary on models that summarize textual evidence extracted from EHR that might support particular hypothesized diagnoses. We envision an interactive system in which this model is used by the radiologist to surface textual evidence that supports different potential conditions that might be suggested by the imaging. Radiologists (and other domain experts) rely on heuristics — type 1 thinking — when making decisions under time constraints. This results in various cognitive biases influencing diagnoses, and these have been shown to be the source of a significant fraction of diagnostic errors in radiology. We propose a novel secondary use of the NLP models to be developed for this project as a means of counteracting these cognitive biases. Specifically, once the radiologist has indicated an initial potential diagnosis via a natural language query, we will automatically present a few alternative plausible diagnosis and summaries of the extracted evidence supporting these (alongside the summary of evidence relevant to the initial query). These alternative diagnoses will be gleaned from gamuts or published lists of differential diagnoses, and we will re-rank them in order of their predicted probability for the current patient according a trained machine learning model. We will evaluate the proposed models in practice at Brigham and Women's Hospital, and assess the degree to which integrating automatically generated summaries actually affects clinical decision-making at point of care.

项目摘要 提高影像质量的电子病历目标神经文本摘要 诊断学 电子健康记录(EHR)包含丰富的患者信息，可以为诊断提供信息 和治疗性决策。然而，这些信息中的大部分都是非结构化的(即，自由文本)。这 使得很难在冗长的文档中找到可能为给定决策提供信息的几个相关注释 患者记录，进而使隐藏在EHR中的关键信息实际上无法对域进行访问 专家在时间有限的情况下工作。因此，临床决策通常是在没有 所有可用数据的优势。我们建议设计、培训和部署新的自然语言处理 (NLP)模型，提供EHR内自由文本数据的摘要，条件是 特定的查询；其目的是让这样的模型帮助诊断和决策。我们还建议 使用这些模型来尝试和抵消领域专家给临床实践带来的认知偏差。 我们特别关注放射学的重要和说明性领域，尽管这种方法将 推广到其他专业。进行影像诊断的放射科医生没有足够的时间 仔细阅读存储在EHR中的患者病历；他们必须凑合使用有限的 解释成像时的背景信息。我们将在我们的初步模型的基础上 总结从电子病历中提取的可能支持特定假设诊断的文本证据。 我们设想了一个交互系统，在该系统中，放射科医生可以使用该模型来显示文本 支持成像可能提示的不同潜在情况的证据。 放射科医生(和其他领域的专家)在做决定时依赖于启发式的第一类思维 在时间限制下。这导致了影响诊断的各种认知偏差，这些偏差 已被证明是放射学中相当大一部分诊断错误的来源。我们提议写一部小说 二次使用将为本项目开发的NLP模型，作为抵消这些影响的手段 认知偏见。具体地说，一旦放射科医生通过自然的 语言查询，我们将自动呈现几个备选的似是而非的诊断和总结 提取了支持这些问题的证据(连同与最初询问相关的证据摘要)。 这些替代诊断将从游戏或已公布的鉴别诊断列表中收集，以及 我们将按照他们对当前患者的预测概率顺序对他们进行重新排序 机器学习模型。我们将评估建议的模式在布里格姆和妇女的实践中 医院，并评估集成自动生成的摘要实际影响的程度 护理点的临床决策。