PheBC: bias correction methods for EHR derived phenotype

PheBC：EHR 衍生表型的偏差校正方法

• 批准号: 10471166
• 负责人: Yong Chen
• 金额: $ 34.2万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10471166
• 关键词: Adverse event; Algorithms; Cations; Chronic; Clinical; Clinical Investigator; Clinical Research; Computer software; Data; Data Science; Data Set; Electronic Health Record; Engineering; Evaluation; Failure; Feasibility Studies; Goals; Health; Health system; Individual; Informatics; Information Retrieval; Investigation; Joints; Knowledge; Knowledge Discovery; Lead; Measurement; Medical; Methodology; Methods; Modeling; Modernization; Non-Insulin-Dependent Diabetes Mellitus; Outcome; Paper; Patients; Pennsylvania; Phenotype; Pilot Projects; Population; Procedures; Publishing; Reproducibility; Reproducibility of Results; Research; Research Personnel; Risk Factors; Sampling Studies; Statistical Models; System; Texas; Translational Research; Universities; Validation; base; cohort; health data; high standard; improved; multiple datasets; novel; outcome prediction; phenotyping algorithm; response; software development; tool

Project Summary In response to the (PAR-18-896), the overarching goal of this proposal is to fully develop a joint effort between statisticians, medical informaticians, clinicians with a focus on developing a rigorous bias correction framework through modern knowledge engineering and data-driven statistical modeling, for improving the unbiasedness and reproducibility of health system data driven research. In this proposal, we will focus on: (1) Develop a novel prior-knowledge-guided integrated likelihood approach to enable bias correction by incorporating prior phenotyping accuracy. (2) Develop methods and algorithms to account for EHR phenotyping errors in both outcomes and predictors. And (3) Validation, Application and Software development. We will use the proposed bias correction methods to several EHR datasets to replicate existing findings and investigate new hypothesis in multiple datasets at University of Texas and University of Pennsylvania. We will also develop software for the proposed methods to facilitate ongoing EHR-based clinical studies.

项目摘要 根据（PAR-18-896），本提案的总体目标是充分开发 统计学家、医学信息学家、临床医生共同努力， 通过现代知识工程和数据驱动， 统计建模，用于提高卫生系统数据的无偏性和再现性 驱动研究。 在本研究中，我们将着重于：（1）开发一种新的先验知识引导的集成 可能性方法，通过结合先前的表型准确性来实现偏倚校正。（二） 开发方法和算法，以解释EHR表型错误的结果， 预测器以及（3）验证、应用和软件开发。我们将使用建议的 对几个EHR数据集的偏差校正方法，以复制现有的研究结果并调查 在德克萨斯大学和宾夕法尼亚大学的多个数据集上的新假设。我们 还将为拟议的方法开发软件，以促进正在进行的基于EHR的临床 问题研究