Probabilistic modeling of observational clinical data for high-throughput inference of disease phenotypes

用于疾病表型高通量推断的观察性临床数据的概率建模

• 批准号: 10432047
• 负责人: Victor Alfonso Rodriguez
• 金额: $ 5.18万
• 依托单位: COLUMBIA UNIVERSITY HEALTH SCIENCES
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-07-01 至 2023-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10432047
• 关键词: Address; Adopted; Adoption; Algorithms; Biological Process; Characteristics; Clinical; Clinical Data; Clinical Informatics; Communities; Consumption; Custom; Data; Data Analyses; Data Science; Disease; Disease Progression; Disease model; Electronic Health Record; Engineering; Ensure; Family; Goals; Gold; Health; Healthcare; Individual; Informatics; Infrastructure; Institution; Knowledge; Label; Literature; Manuals; Maps; Medical; Methods; Modeling; Outcome; Pattern; Phenotype; Population; Process; Production; Public Health; Research; Resolution; Running; Series; Statistical Models; System; Testing; Time; Uncertainty; Work; base; cohort; comorbidity; data modeling; design; disease phenotype; disorder subtype; health data; improved; insight; knowledgebase; public health research; repository; tool; trait; trend

PROJECT SUMMARY/ABSTRACT Today's healthcare infrastructure supports the production and storage of clinical data on a massive scale. A central goal in clinical informatics is to leverage these data to improve our understanding of health and disease. However, a major challenge is the paucity of reliable disease labels in observational data. Disease phenotypes address this issue by summarizing the characteristics of specific diseases in terms of commonly observed clinical variables. Classically, disease phenotypes are engineered via a manual expert-driven approach which fails to scale to large numbers of diseases. Data-driven methods for disease phenotyping aim to obtain large numbers of disease phenotypes by directly modeling large-scale observational clinical data. Such high-throughput methods may scale, but generally cannot guarantee identifiability; that is, inferred phenotypes are not guaranteed to map to specific diseases. In addition, data-driven disease phenotyping methods generally model phenotypes independently with no effort to capture relationships among diseases which would be consistent with our understanding of comorbidities, disease progression trends, and disease type/subtype relationships. The long-term goal of the proposed research is to support large-scale analysis of observational clinical data by introducing a family of closely related models for high-throughput disease phenotyping which resolve the issue of identifiability and model relationships among diseases. My work is inspired by an unsupervised probabilistic graphical model for high-throughput phenotyping, UPhenome. My objective is to derive, implement, validate, and disseminate UPhenome-based models which will 1) process both biomedical knowledge and clinical data to yield identifiable phenotypes and 2) model co-occurrence, temporal, and hierarchical relationships among inferred phenotypes. My central hypothesis is that UPhenome-based models can support large-scale clinical data analysis by inferring phenotypes that effectively represent the clinical characteristics of specific diseases while also capturing common comorbidities (co- occurrence model), patterns of disease progression (temporal model), and organizing diseases into types and subtypes (hierarchical model). To test this hypothesis, I propose the following aims. Aim 1: I describe Guided UPhenome, a model which process biomedical knowledge and clinical data to yield identifiable phenotypes. The model's capacity for capturing disease-specific traits is evaluated qualitatively by clinical experts, and quantitatively in disease-specific cohort selection tasks versus a gold-standard and a competing algorithm. Aim 2: I detail extensions to UPhenome which allow for modeling of disease relationships. The meaningfulness of these relationships is evaluated qualitatively using a series of custom “intrusion tasks” inspired by the topic modeling literature. Aim 3: I will disseminate UPhenome-based models by ensuring their compatibility with the Observational Medical Outcomes Partnership (OMOP) common data model, and promoting their adoption within the Observational Health Data Sciences and Informatics (OHDSI) community.

项目摘要/摘要 当今的医疗基础设施支持大规模的临床数据的生产和存储。一个 临床信息的核心目标是利用这些数据来提高我们对健康和疾病的理解。 但是，主要的挑战是观察数据中可靠的疾病标签的匮乏。疾病表型 通过总结特定疾病的特征来解决此问题 变量。从经典上讲，疾病表型是通过手动专家驱动的方法进行设计的，该方法未能 扩展到大量疾病。疾病表型的数据驱动方法旨在获得大量 通过直接对大规模观察临床数据进行建模来建模疾病表型。这样的高通量 方法可能会扩展，但通常无法保证身份；也就是说，推断的表型不是 保证将其映射到特定疾病。此外，数据驱动的疾病表型方法通常建模 表型独立而没有努力捕捉疾病之间的关系，这与 我们对合并症，疾病进展趋势和疾病类型/亚型关系的理解。 拟议研究的长期目标是支持观察性临床数据的大规模分析 通过引入一个密切相关的高通量疾病表型的模型，该模型解决了 疾病之间的身份和模型关系问题。我的工作灵感来自无监督的 高通量表型的概率图形模型，异味。我的目标是得出 实施，验证和传播基于异味的模型，该模型将1）处理这两种生物医学知识 和临床数据以产生可识别的表型和2）模型共发生，临时和分层 推断的表型之间的关系。我的核心假设是基于异味的模型可以 通过推断有效代表的表型来支持大规模临床数据分析 特定疾病的临床特征，同时还捕获常见合并症 发生模型），疾病进展模式（时间模型）和组织疾病 分为类型和亚型（分层模型）。为了检验这一假设，我提出了以下目的。 目的1：我描述了指导性的杜松子组，该模型是处理生物医学知识和临床数据以产生的模型 可识别的表型。该模型的捕获特异性性状的能力通过定性评估 临床专家，并且在疾病特异的队列选择任务中进行定量与金标准和 竞争算法。目的2：我详细介绍了对异味的扩展，这允许对疾病关系进行建模。 这些关系的有意义是使用一系列自定义“入侵任务”定性评估的 受主题建模文献的启发。目标3：我将通过确保他们的模型来传播基于异味的模型 与观察医学结果伙伴关系（OMOP）共同数据模型的兼容性，以及 在观察健康数据科学和信息学（OHDSI）社区中促进其采用。

项目成果

Phenotype Inference with Semi-Supervised Mixed Membership Models.

使用半监督混合会员模型进行表型推断。

• 发表时间: 2019
• 期刊: Proceedings of machine learning research
• 作者: Rodriguez,VictorA;Perotte,Adler
• 通讯作者: Perotte,Adler