Multi-objective representation learning methods for interpetable predictions of patient outcomesusing electronic health records

使用电子健康记录对患者结果进行可重复预测的多目标表示学习方法

• 批准号: 10453863
• 负责人: William La Cava
• 金额: $ 23.66万
• 依托单位: BOSTON CHILDREN'S HOSPITAL
• 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 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10453863
• 关键词: Address; Affect; Archives; Area; Automobile Driving; Cardiovascular Diseases; Categories; Clinical; Communities; Complex; Couples; Data; Data Reporting; Data Set; Databases; Development; Disease; Electronic Health Record; Engineering; Feedback; Goals; Graph; Hand; Health; Health Sciences; Health system; Heart Diseases; Heart failure; Hospitals; Inpatients; Knowledge; Learning; Machine Learning; Measurement; Measures; Mentors; Methodology; Methods; Mining; Modeling; Nature; Outcome; Pathology; Patient Care; Patient-Focused Outcomes; Patients; Pennsylvania; Performance; Pharmaceutical Preparations; Phase; Population; Process; Property; Protocols documentation; Quality of life; Recommendation; Replacement Arthroplasty; Research; Research Personnel; Risk; Structure; Techniques; Testing; Text; Time; Training; Translating; University Hospitals; Visit; Work; archive data; archived data; base; care costs; cluster computing; data complexity; deep learning; deep neural network; design; disease diagnosis; disorder subtype; heart disease risk; high dimensionality; hospital readmission; improved; insight; learning strategy; machine learning method; network architecture; neural network; novel; open source tool; operation; patient health information; point of care; predictive modeling; readmission rates; readmission risk; statistical and machine learning

Project Summary/Abstract This project proposes new methods for representing data in electronic health records (EHR) to improve pre- dictive modeling and interpretation of patient outcomes. EHR data offer a promising opportunity for advancing the understanding of how clinical decisions and patient conditions interact over time to influence patient health. However, EHR data are difficult to use for predictive modeling due to the various data types they contain (con- tinuous, categorical, text, etc.), their longitudinal nature, the high amount of non-random missingness for certain measurements, and other concerns. Furthermore, patient outcomes often have heterogenous causes and re- quire information to be synthesized from several clinical lab measures and patient visits. The core challenge at hand is overcoming the mismatch between data representations in the EHR and the assumptions underly- ing commonly used statistical and machine learning (ML) methods. To this end, this project proposes novel wrapper-based methods for learning informative features from EHR data. Both methods propose specialized operators to handle sequential data, time delays, and variable interactions, and have the capacity to discover underlying clinical rules/decisions that affect patient outcomes. Importantly, both methods also produce archives of possible models that represent the best trade-offs between complexity and accuracy, which assists in model interpretation. These method advances are made possible by encoding a rich set of data operations as nodes in a directed acyclic graph, and optimizing the graph structures using multi-objective optimization. The central hypothesis of this research is that multi-objective optimization can learn effective data representations from the EHR to produce accurate, explanatory models of patient outcomes. Preliminary work has shown that these methods can effectively learn low-order data representations that improve the predictive ability of several state- of-the-art ML methods. This technique demonstrates good scaling properties with high-dimensional biomedical data. Aim 1 (K99) is to develop a multi-objective feature engineering method that pairs with existing ML methods to iteratively improve their performance by constructing new features from the raw data and using feedback from the trained model to guide feature construction. In Aim 2 (K99), this method is applied to form predictive models of the risk of heart disease and heart failure using longitudinal EHR data. The resultant models will be inter- preted with the help of mentors in order to translate predictions into clinical recommendations. For Aim 3 (R00), a second method is proposed that uses a similar framework to optimize existing neural network approaches in order to simplify their structure as much as possible while maintaining accuracy. The goal of Aim 4 (R00) is to identify hospital patients who are at risk of readmission and propose point-of-care strategies to mitigate that risk. This goal is facilitated through the application of the proposed methods to patient data collected from the Hospital of the University of Pennsylvania, the Geisinger Health System, and publicly available EHR databases.

项目摘要/摘要 该项目提出了代表电子健康记录（EHR）中数据的新方法，以改善前 对患者预后的命令建模和解释。 EHR数据为前进提供了有前途的机会 对临床决策和患者状况如何随着时间的推移影响患者健康的理解。 但是，由于它们包含的各种数据类型，EHR数据很难用于预测建模（ 脆弱，分类，文本等），它们的纵向性质，一定的非随机失踪量 测量和其他问题。此外，患者的结局通常具有异质原因和重新 要求从几个临床实验室措施和患者就诊中综合的信息。核心挑战 手头正在克服EHR中的数据表示和低估的假设之间的不匹配 常用的统计和机器学习（ML）方法。为此，这个项目建议小说 从EHR数据中学习信息功能的基于包装器的方法。两种方法建议专业 操作员处理顺序数据，时间延迟和可变交互，并具有发现的能力 影响患者预后的基本临床规则/决策。重要的是，这两种方法还产生档案 代表复杂性和准确性之间最佳权衡的可能模型，这些模型有助于模型 解释。通过将丰富的数据操作编码为节点，可以实现这些方法的进步 在定向的无环图中，并使用多目标优化优化图形结构。中央 这项研究的假设是多目标优化可以从中学习有效的数据表示 EHR产生精确的患者结局模型。初步工作表明这些 方法可以有效地学习低阶数据表示，以提高几个状态的预测能力 ART ML方法。该技术具有高维生物医学的良好缩放特性 数据。 AIM 1（K99）是开发一种多目标功能工程方法，该方法与现有ML方法配对 通过从原始数据中构造新功能并使用来自 训练有素的模型来指导特征结构。在AIM 2（K99）中，该方法用于形成预测模型 使用纵向EHR数据患心脏病和心力衰竭的风险。结果模型将相互间 在导师的帮助下，将预测转化为临床建议。对于AIM 3（R00）， 提出了第二种方法，该方法使用类似的框架来优化现有的神经网络方法 为了在保持准确性的同时，尽可能简化其结构。目标4（R00）的目标是 确定有入院风险和提案策略的医院患者，以减轻这种情况 风险。通过将提出的方法应用于从从该数据中收集的患者数据中的数据来准备该目标 宾夕法尼亚大学医院，盖辛格卫生系统以及公开可用的EHR数据库。