Developing scalable algorithms to incorporate unstructured electronic health records for causal inference based on real-world data

开发可扩展的算法以合并非结构化电子健康记录，以基于真实世界数据进行因果推断

• 批准号: 10581591
• 负责人: JOSHUA K LIN
• 金额: $ 64.48万
• 依托单位: BRIGHAM AND WOMEN'S HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-06-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10581591
• 关键词: Address; Algorithms; Clinical; Clinical Research; Code; Cohort Studies; Comparative Effectiveness Research; Complex; Confounding Factors (Epidemiology); Consumption; Data; Data Set; Data Sources; Databases; Electronic Health Record; Elements; Empirical Research; Ensure; Environment; Evaluation; Future; Healthcare; Healthcare Systems; Influentials; Knowledge; Knowledge acquisition; Left; Link; Machine Learning; Manuals; Massachusetts; Maximum Likelihood Estimate; Medicaid; Medical; Medicare; Methods; Modeling; Names; Natural Language Processing; North Carolina; Operative Surgical Procedures; Patient Care; Patient-Focused Outcomes; Patients; Pattern; Performance; Physicians; Probability; Property; Proxy; Randomized, Controlled Trials; Reporting; Research; Research Design; Research Personnel; Risk; Risk Factors; Semantics; Severities; Specific qualifier value; Stratification; Structure; Symptoms; System; Techniques; Testing; Texas; Text; Therapeutic; Time; Training; Treatment outcome; Validation; Work; analytical method; care delivery; comparative effectiveness study; comparison control; comparison group; computerized; cost; disease prognosis; disorder risk; eHealth; electronic health database; electronic health information; electronic health record system; evidence base; flexibility; health care service utilization; high dimensionality; improved; innovation; machine learning method; novel strategies; operation; preservation; randomized trial; research study; routine care; safety study; simulation; sound; tool; treatment choice; unstructured data

Project Summary/Abstract The routine operation of the US Healthcare system produces an abundance of electronically-stored data that captures the care of patients as it is provided in settings outside of controlled research environments. The potential for utilizing these data to inform future treatment choices and improve patient care and outcomes of all patients in the very system that generates the data is widely acknowledged. Given these key properties of the routine-care data and the abundance of electronic healthcare databases covering millions of patients, it is critical to strengthen the rigor of analyses of such data. Our group has previously developed an analytic approach to reduce bias when analyzing routine-care databases, which has proven effective in more than 50 empirical research studies across a range of topics and data sources. However, this approach currently cannot incorporate free-text information that is recorded in electronic health records, such as clinical notes and reports. This limitation has left a large amount of rich patient information underutilized for clinical research. We thus aim to adapt and refine a set of established computerized natural language processing algorithms that can identify and extract useful information from the clinical notes and reports in electronic health records and incorporate them into our validated analytical approach for balancing background risks of different comparison groups, a key step to ensure fair evaluation when comparing different therapeutic options. To test this newly integrated and augmented approach, we will implement and adapt it in simulation studies where we can evaluate and improve the performance of these new analytic methods in a controlled but realistic fashion. In addition, we will assess the performance of our new approach in 8 practical studies comparing medical or surgical treatments that are highly relevant to patients. To ensure highest level of data completeness and quality, we have linked multiple healthcare utilization (claims) databases, spanning from 2007 to 2016, with 3 electronic health records systems, including one each in Massachusetts, North Carolina, and Texas. This data will allow testing of our newly integrated approach in a variety of care delivery systems and data environments, which will be very informative for the application of our products in the real-world settings.

项目摘要/摘要 美国医疗保健系统的常规操作会产生大量的电子存储数据 捕获在受控研究环境之外的设置中提供的患者的护理。这 利用这些数据为未来的治疗选择提供信息，并改善患者护理和所有人的结果 生成数据的系统中的患者被广泛认可。考虑到这些关键特性 常规护理数据和涵盖数百万患者的电子医疗保健数据库的丰富性，这是至关重要的 加强了此类数据分析的严格性。我们的小组以前已经开发了一种分析方法 分析常规数据库时降低偏见，这在50多个经验中被证明有效 跨各种主题和数据源的研究。但是，这种方法目前无法合并 在电子健康记录中记录的自由文本信息，例如临床注释和报告。这 限制已经使大量丰富的患者信息用于临床研究。因此，我们的目标是 适应并完善一组既定的计算机化自然语言处理算法，这些算法可以识别和 从电子健康记录中的临床笔记和报告中提取有用的信息并将其合并 进入我们经过验证的分析方法，以平衡不同比较组的背景风险，这是关键步骤 比较不同的治疗选择时确保公平评估。测试这个新的整合，并 增强方法，我们将在模拟研究中实施并适应它，在该研究中我们可以评估和改进 这些新分析方法的性能以受控但现实的方式。此外，我们将评估 我们在8个实际研究中的新方法的表现，比较了医学或外科治疗 与患者高度相关。为了确保最高水平的数据完整性和质量，我们已经链接了多个 医疗保健利用率（索赔）数据库，涉及2007年至2016年，具有3个电子健康记录系统， 包括一个在马萨诸塞州，北卡罗来纳州和德克萨斯州。这些数据将允许我们新的测试 各种护理交付系统和数据环境中的集成方法，这将非常有用 用于在现实世界中应用我们的产品。