Statistical Methods for Incorporating Machine Learning Tools in Inference and Large-Scale Surveillance using Electronic Medical Records Data

使用电子病历数据将机器学习工具纳入推理和大规模监控的统计方法

• 批准号: 10206237
• 负责人: Marco Carone
• 金额: $ 48.62万
• 依托单位: UNIVERSITY OF WASHINGTON
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-18 至 2024-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10206237
• 关键词: Algorithms; Benefits and Risks; Characteristics; Clinical Data; Complex; Computer software; Computerized Medical Record; Confidence Intervals; Country; Data; Data Collection; Data Set; Detection; Dimensions; E-learning; Early Diagnosis; Effectiveness; Electronic Health Record; Ensure; Epidemiology; Estimation Techniques; Event; Frequencies; Goals; Health; Healthcare; Heterogeneity; Information Systems; Infrastructure; Intervention; Knowledge; Learning; Link; Machine Learning; Measures; Methodology; Methods; Modernization; Monitor; Outcome; Patient-Focused Outcomes; Patients; Pharmacodynamics; Population; Population Surveillance; Procedures; Public Health; Records; Reproducibility; Research; Research Methodology; Research Personnel; Safety; Sentinel; Signal Transduction; Standardization; Statistical Methods; Stream; Structural Models; Subgroup; Surveillance Program; System; Techniques; Testing; Time; Treatment outcome; Update; base; clinical care; comparative treatment; data streams; flexibility; high dimensionality; improved; interest; machine learning method; national surveillance; novel; open source; patient population; patient subsets; risk minimization; software development; surveillance data; tool; treatment effect; user-friendly

SUMMARY The modernization and standardization of clinical care information systems is creating large networks of linked electronic health records (EHR) that capture key treatments and select patient outcomes for millions of patients throughout the country. The observational data emerging from these systems provide an unparalleled opportunity to learn about the effectiveness of existing and novel treatments, and to monitor potential safety issues that may arise when interventions are used in broad patient populations. However, observational clinical data have exposures that are driven by many factors and therefore aggressive adjustment is needed to remove as much confounding bias as possible in order to make attribution regarding select exposures. The field of machine learning provides a powerful collection of data-driven approaches for performing flexible, thorough confounding adjustment, but performing reliable statistical inference is particularly challenging when these techniques are used as part of the analytic strategy. We propose to advance reproducible research methods by developing and illustrating novel targeted learning tools that leverage the flexibility of machine learning methods to detect and characterize health effect signals using large-scale EHR data. Specifically, we will first develop techniques for making efficient, statistically valid and robust inference for treatment effects using state-of-the-art machine learning tools. We will also develop online learning techniques to make such inference in the context of streaming EHR data. Methodological advances will enable us to formulate a formal, rigorous and practical framework for conducting continuous, effective and reliable surveillance for safety endpoints. Finally, we will develop statistical approaches for incorporating prior information -- including demographic, epidemiologic or pharmacodynamic knowledge, for example -- to improve health effect estimation and inference when the health outcome of interest is rare and the statistical problem is thus difficult, as often occurs in safety surveillance. The ultimate goal of the proposed research is to enable biomedical researchers and public health regulators to carefully monitor and protect the health of the public by allowing them to more effectively and more reliably detect critical health effect signals that may be contained in population-scale EHR data.

概括 临床护理信息系统的现代化和标准化正在建立大型网络 链接的电子健康记录（EHR）捕获关键治疗并选择患者的结果 全国数百万患者。从这些系统中出现的观察数据 提供无与伦比的机会来了解现有和新颖治疗的有效性， 并监视当广泛患者使用干预措施时可能出现的潜在安全问题 人群。但是，观察性临床数据的暴露是由许多因素驱动的， 因此，需要进行积极的调整以消除尽可能多的混淆偏见以进行 就某些暴露量进行归因。机器学习领域提供了强大的 收集数据驱动的方法，用于执行灵活，彻底的混淆调整，但 当将这些技术用作可靠的统计推断时，尤其具有挑战性 分析策略的一部分。我们建议通过开发和 说明新颖的目标学习工具，这些工具利用机器学习方法的灵活性 使用大型EHR数据检测并表征健康效应信号。 具体而言，我们将首先开发出高效，统计上有效且健壮的推理的技术 用于使用最先进的机器学习工具的治疗效果。我们还将开发在线学习 在流ehr数据的上下文中进行这种推断的技术。方法学的进步将会 使我们能够制定一个正式，严格和实用的框架，以进行连续，有效 和可靠的安全端点监视。最后，我们将开发统计方法 并入先前的信息 - 包括人口统计学，流行病学或药效学 例如，知识 - 改善健康结果时的健康效应估计和推断 有趣的是很少见，因此统计问题很困难，因为在安全监视中经常发生。 拟议研究的最终目标是启用生物医学研究人员和公共卫生 监管机构通过允许他们更有效地监视和保护公众的健康 并更可靠地检测到可能包含在人群级EHR中的关键健康效应信号 数据。