Big Data Methods for Comprehensive Similarity based Risk Prediction

基于大数据的综合相似性风险预测方法

• 批准号: 10551349
• 负责人: KRZYSZTOF KIRYLUK
• 金额: $ 45.57万
• 依托单位: COLUMBIA UNIVERSITY HEALTH SCIENCES
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-02-12 至 2025-01-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10551349
• 关键词: Address; Automation; Big Data; Big Data Methods; Biological Markers; Biological Process; Biometry; Case Study; Characteristics; Chronic; Chronic Disease; Chronic Kidney Failure; Classification; Clinical; Clinical Data; Clinical Medicine; Complex; Data; Data Reporting; Data Science; Derivation procedure; Diagnosis; Disease; Disease Progression; Electronic Health Record; End stage renal failure; Environment; Etiology; Exhibits; Exposure to; Genetic; Genomics; Goals; Health Professional; Healthcare; Heterogeneity; Human; Individual; Informatics; Interdisciplinary Study; Intervention; Knowledge; Length; Life; Literature; Machine Learning; Medical; Medical Genetics; Medical Records; Methods; Modeling; Natural Language Processing; Outcome; Patients; Pharmaceutical Preparations; Population; Preparation; Reporting; Reproducibility; Research; Risk; Social Environment; Source; Surveys; Techniques; biomedical informatics; clinical decision support; clinical decision-making; clinical phenotype; clinical risk; data analysis pipeline; data modeling; data standards; design; disease diagnosis; feature selection; health assessment; health data; health determinants; improved; interoperability; mortality risk; novel; open data; open source; outcome prediction; patient health information; patient population; precision medicine; predict clinical outcome; risk prediction; socioeconomics; support tools; vector

Project Summary Electronic health records (EHR) provide rich source of data about representative populations and are yet to be fully utilized to enhance clinical decision-making. Conventional approaches in clinical decision-making start with the identification of relevant biomarkers based on subject-matter knowledge, followed by detailed but limited analysis using these biomarkers exclusively. As the current scientific literature indicates, many human disorders share a complex etiological basis and exhibit correlated disease progression. Therefore, it is desirable to use comprehensive patient data for patient similarity. This proposal focuses on deriving a comprehensive and integrated score of patient similarity from complete patient characteristics currently available, including but not limited to 1) demographic similarity; 2) genetic similarity; 3) clinical phenotype similarity; 4) treatment similarity; and 5) exposome similarity (here exposome defined as all available attributes of the living environment an individual is exposed to), when some of the aspects may overlap and interact. We will optimize information fusion and task-dependent feature selection for assessing patient similarity for clinical risk prediction. Since currently there does not exist a pipeline that is able to extract executable complete patient determinant data, to achieve the research goal described above, we propose first deliver an open- source data preparation pipeline that is based on a widely used clinical data standard, the OMOP (Observational Medical Outcomes Partnership) Common Data Model (CMD) version 5.2. Moreover, to mitigate common missingness and sparsity challenges in clinical data, we describe the first attempt to represent patients' sparse clinical information with missingness, including diagnosis information, medication data, treatment intervention, with a fixed-length feature vector (i.e. the Patient2Vec). This project has four specific aims. Aim 1 is to develop a clinical data processing pipeline for harmonizing patient information from multiple sources into a standards-based uniformed data representation and to evaluate its efficiency, interoperability, and accuracy. Aim 2 is to leverage a powerful machine learning technique, Document2Vec, from the natural language processing literature, to create an open-source Patient2Vec framework for the derivation of informative numerical representations of patients. Aim 3 is to develop a unified machine learning clinical- outcome-prediction framework for Optimized Patient Similarity Fusion (OptPSF) that integrates traditional medical covariates with the derived numerical patient representations from Patient2Vec (Aim 2) for improved clinical risk prediction. Aim 4 is to evaluate our similarity framework for predicting 1) the risk of end-stage kidney disease (ESKD) in general EHR patient population and 2) the risk of death among patients with chronic kidney disease (CKD).

项目概要 电子健康记录 (EHR) 提供了有关代表性人群的丰富数据来源，但仍有待完善 充分利用来增强临床决策。临床决策中的传统方法开始 根据主题知识识别相关生物标志物，然后进行详细但 仅使用这些生物标志物进行有限的分析。正如当前的科学文献表明，许多人类 疾病具有复杂的病因学基础并表现出相关的疾病进展。因此，它是 希望使用全面的患者数据来确定患者的相似性。该提案的重点是导出 目前根据完整的患者特征对患者相似性进行综合综合评分 可用，包括但不限于 1) 人口统计相似性； 2）遗传相似性； 3) 临床表型 相似; 4）治疗相似度； 5）暴露组相似性（这里暴露组定义为所有可用属性 个人所接触的生活环境），其中某些方面可能重叠和相互作用。我们 将优化信息融合和任务相关的特征选择，以评估临床患者的相似性 风险预测。由于目前不存在能够完整提取可执行文件的管道 患者决定因素数据，为了实现上述研究目标，我们建议首先提供一个开放的 基于广泛使用的临床数据标准 OMOP 的源数据准备管道 （观察医疗结果合作伙伴关系）通用数据模型 (CMD) 5.2 版。此外，为了减轻 临床数据中常见的缺失和稀疏挑战，我们描述了代表的第一次尝试 患者临床信息稀疏且缺失，包括诊断信息、用药数据、 治疗干预，具有固定长度的特征向量（即 Patient2Vec）。该项目有四个具体内容 目标。目标 1 是开发一个临床数据处理管道，用于协调来自多个方面的患者信息 源转化为基于标准的统一数据表示并评估其效率、互操作性、 和准确性。目标 2 是利用来自自然的强大机器学习技术 Document2Vec 语言处理文献，创建一个开源 Patient2Vec 框架来推导 患者的信息性数字表示。目标 3 是开发一个统一的机器学习临床- 优化患者相似性融合 (OptPSF) 的结果预测框架集成了传统的 医学协变量与从 Patient2Vec（目标 2）导出的数字患者表示，以改进 临床风险预测。目标 4 是评估我们用于预测 1) 末期风险的相似性框架 一般 EHR 患者群体中的肾脏疾病 (ESKD) 以及 2) 慢性肾病患者的死亡风险 肾脏疾病（CKD）。