Novel deep learning strategy to translate ICD Codes to the Abbreviated Injury Scale

将 ICD 代码转换为缩写伤害量表的新颖深度学习策略

• 批准号: 10532796
• 负责人: Thomas Ryan Hartka
• 金额: $ 8.08万
• 依托单位: UNIVERSITY OF VIRGINIA
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-12-01 至 2023-11-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10532796
• 关键词: Abbreviations; Accident and Emergency department; Address; Algorithms; American College of Surgeons; Anatomy; Biomechanics; Body Regions; Cause of Death; Certification; Cessation of life; Child; Classification; Code; Comparative Effectiveness Research; Computational Linguistics; Data; Data Science; Databases; Diagnosis; Disease; Disparity; Effectiveness of Interventions; Elements; Emergency Medicine; European Union; Goals; Grant; Individual; Injury; Injury Severity Score; International; International Classification of Disease Codes; International Classification of Diseases; Intervention; K-Series Research Career Programs; Language; Language Development; Learning Module; Life; Location; Machine Learning; Maps; Measurement; Measures; Medical; Methods; Modeling; Modernization; Monitor; National Center for Advancing Translational Sciences; Natural Language Processing; Outcome; Patients; Pattern; Policies; Population; Prevention Research; Research; Risk Factors; Safety; Science; Severities; Specific qualifier value; System; Techniques; Training; Translating; Translations; Trauma; Trauma Research; Trauma patient; Traumatic injury; Vehicle crash; Work; World Health Organization; administrative database; care delivery; comparative effectiveness; data integration; data interoperability; data repository; deep learning; deep learning model; disability; disease diagnosis; improved; individual patient; injury prevention; injury surveillance; innovation; learning strategy; mortality; novel; novel strategies; predictive modeling; programs; recurrent neural network; relative effectiveness; severe injury; success; tool; trauma care; vector

PROJECT SUMMARY Trauma is one of the leading causes of death and disability in the US and around the world. Accurate measurement is critical to improving our understanding of this disease and gauging the effectiveness of interventions. Tracking the burden of traumatic injuries relies on not only identifying deaths, but also non-fatal injuries. The widely used International Classification of Disease (ICD) diagnosis coding system, developed by the World Health Organization. does not have a mechanism for directly measuring injury severity. In order to measure in severity, ICD codes are often converted to the Abbreviated Injury Scale (AIS). Each AIS code has a measure of relative injury severity, and multiple codes can be combined to determine the overall injury severity of an individual patients. However, the currently used methods for conversion of ICD to AIS rely on one-to-one mapping between these coding systems, which has many inherent difficulties. Specifically, these one-to-one mappings have been shown to systematically underestimate overall injury severity. Recent advances in computation linguistics have solved very similar problems with the use of embedding and deep learning. We intended to apply these techniques ICD to AIS translations. The key innovation is to consider all the information available about a patient simultaneously, rather than converting each code in isolation. This objective of this R03 proposal is to develop tools that improve the accuracy of population-level injury research that uses ICD codes. We will accomplish this objective by: (1) developing a tool to predict overall injury severity for individual patients from ICD codes, and (2) developing a tool to translate ICD codes to AIS for individual patients. Modern language translation has algorithms are based on determining the location of words in an embedded space, so words with similar meaning are near to each other and the relative locations encode relationships between words. Similarly, we will transfer ICD into an embedded space, which will be used by subsequent deep learning modules produce our results. There is data for millions of trauma patients collected in in the National Trauma Data Bank (NTDB) that contains both ICD and AIS extracted by expert coders. We will use this data to train and evaluate the deep learning models that will underlie our tools. Together, these tools will meet the critical needs to improve the quality of trauma research and increase the accuracy of injury monitoring using administrative medical databases.

项目摘要 创伤是美国和世界各地死亡和残疾的主要原因之一。准确的 测量对于提高我们对这种疾病的理解并衡量的有效性至关重要 干预措施。跟踪创伤伤害的负担不仅依赖于识别死亡，而且还取决于非致命的死亡 受伤。广泛使用的国际疾病分类（ICD）诊断编码系统，由 世界卫生组织。没有直接测量损伤严重程度的机制。为了 严重程度的度量，ICD代码通常会转换为缩写损伤量表（AIS）。每个AIS代码都有一个 相对伤害严重程度和多个代码的度量可以合并以确定总体伤害严重程度 个别患者。但是，当前使用的用于将ICD转换为AIS的方法依赖于一对一 这些编码系统之间的映射，这有许多固有的困难。具体而言，这些一对一 已显示映射系统地低估了总体伤害严重程度。最近的进步 计算语言学解决了使用嵌入和深度学习的非常相似的问题。我们 旨在将这些技术应用于AIS翻译。关键创新是考虑所有信息 同时可用于患者，而不是孤立地转换每个代码。这个目标 R03提案是开发提高使用ICD的人口水平伤害研究准确性的工具 代码。我们将通过：（1）开发一种工具来预测个人的总体伤害严重程度 ICD代码的患者以及（2）开发一种将ICD代码转化为单个患者AIS的工具。现代的 语言翻译的算法是基于确定单词在嵌入式空间中的位置，因此 具有相似含义的单词彼此接近，相对位置编码单词之间的关系。 同样，我们将ICD转移到嵌入式空间中，随后的深度学习模块将使用该空间 产生我们的结果。国家创伤数据库中收集的数百万创伤患者有数据 （NTDB）包含专家编码者提取的ICD和AIS。我们将使用这些数据训练和评估 深度学习模型将是我们工具的基础。这些工具在一起将满足改善的关键需求 创伤研究的质量并使用行政医疗提高伤害监测的准确性 数据库。