Mechanistic Machine Learning

机械机器学习

• 批准号: 9427058
• 负责人: David J. Albers
• 金额: $ 69.87万
• 依托单位: COLUMBIA UNIVERSITY HEALTH SCIENCES
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-20 至 2020-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9427058
• 关键词: Address; Admission activity; Affect; Area; Assimilations; Carbohydrates; Clinical; Clinical Treatment; Complex; Computational Biology; Data; Data Science; Depressed mood; Early Intervention; Eating; Endocrine Physiology; Evaluation; Fingers; Food; Future; Generic Drugs; Glomerular Filtration Rate; Glucose; Goals; Health; Healthcare; Hepatic; Hour; Insulin; Insulin Infusion Systems; Insulin-Dependent Diabetes Mellitus; Intensive Care Units; Intervention; Knowledge; Lead; Learning; Link; Machine Learning; Manuals; Markov chain Monte Carlo methodology; Measurable; Measurement; Measures; Medical; Medicine; Methodology; Methods; Minor Planets; Modeling; Monitor; Non-Insulin-Dependent Diabetes Mellitus; Outcome; Outpatients; Patient-Focused Outcomes; Patients; Phenotype; Physicians; Physiological; Physiology; Power Plants; Property; Publishing; Recommendation; Renal function; Running; System; Techniques; Technology; Testing; Time; Training; Transportation; Treatment outcome; Uncertainty; Validity of Results; Weather; Work; base; clinical phenotype; computerized; control theory; fly; glucose metabolism; glucose monitor; glucose production; health record; improved; individual patient; insight; insulin secretion; interstitial; mathematical model; nutrition; outcome forecast; outcome prediction; personalized learning; personalized medicine; physiologic model; reduced food intake; space travel; treatment strategy

PROJECT SUMMARY / ABSTRACT The goal of this project is to combine empirical data with mechanistic physiologic knowledge to produce personalized, quantitative predictions that can lead to improved treatments. In normal practice, physicians reason by analogy from generic physiologic principles, but the technology exists to exploit even imperfect physiologic models make treatment personalized and quantitatively grounded in physiology, and to improve learning from empirical data. We will apply data assimilation (DA), mechanistic mathematical modeling, machine learning, and control theory, which have revolutionized space travel, weather forecasting, transportation and flight, and manufacturing. Data assimilation and control theory have seen very limited use in medicine, usually applied in data-rich circumstances like continuous glucose monitoring or packemakers. Our previous work demonstrated use of data assimilation with glucose-insulin models to predict glucose in the outpatient type 2 diabetes setting. We will extend data assimilation and control theory using, for example, a constrained ensemble Kalman filter and an offline Markov Chain Monte Carlo algorithm, to better handle sparse, short training sets on rapidly changing patients, and we will apply it in the setting of glucose management in the intensive care unit (ICU). Moreover, we will develop DA for phenotyping applications by exploiting the parameter estimation capabilities of DA. Data assimilation can be used to estimate measureable and unmeasureable physiologic states and parameters, and we will use these estimates to create higher definition phenotypes. While we are focusing on glucose management in the ICU, we will develop methods that are likely to generalize, beginning the effort to develop DA in the context of healthcare more broadly. The work we propose is a necessary step toward being able to use mechanism-driven DA to test, validate and optimize personalized short-term treatment strategies, long-term health forecasts, and mechanistic physiologic understanding. We will carry out the following aims: AIM 1—forecast—extend the DA methodology to allow forecasting, personalization, model evaluation, and model selection in the ICU context, relating treatment input to physiologic outcome; AIM 2—phenotype—extend the DA framework to state and parameter estimation to allow for mechanism-based phenotyping, careful uncertainty quantification, and inference of difficult or impossible-to-measure physiology; AIM 3—control—extend the DA to include a controller that begins with desired clinical outcomes, e.g., glucose range, and estimates the inputs, e.g., insulin or nutrition, required to achieve the outcomes.

项目总结/摘要 这个项目的目标是将联合收割机经验数据与机械生理学知识结合起来， 个性化的、定量的预测，可以改善治疗。在正常情况下，医生 从一般的生理学原理类推，但技术的存在，利用即使是不完善的 生理学模型使治疗个性化，并在生理学上定量化， 从经验数据中学习。我们将应用数据同化（DA），机械数学建模， 机器学习和控制理论，它们彻底改变了太空旅行，天气预报， 运输和飞行，以及制造业。数据同化和控制理论的应用非常有限 在医学上，通常应用于数据丰富的环境，如连续葡萄糖监测或包装。 我们以前的工作表明，使用数据同化与葡萄糖胰岛素模型预测葡萄糖在 门诊2型糖尿病患者。我们将扩展数据同化和控制理论，例如， 约束集合卡尔曼滤波和离线马尔可夫链蒙特卡罗算法，以更好地处理 稀疏，短训练集快速变化的患者，我们将其应用于葡萄糖的设置 重症监护室（ICU）的管理。此外，我们将通过以下方式开发用于表型分析应用的DA： 利用DA的参数估计能力。数据同化可以用来估计可测量的 和不可测量的生理状态和参数，我们将使用这些估计来创建更高的 定义表型。当我们专注于ICU中的葡萄糖管理时，我们将开发方法， 可能会推广，开始在更广泛的医疗保健背景下开发DA的努力。工作 我们提出的是一个必要的步骤，能够使用机制驱动的DA测试，验证和优化 个性化的短期治疗策略、长期健康预测和机械生理学 认识 我们将实现以下目标：AIM 1-预测-扩展DA方法以允许预测， ICU环境中的个性化、模型评估和模型选择，将治疗输入与 AIM 2-表型-将DA框架扩展到状态和参数估计， 允许基于机制的表型分析，仔细的不确定性量化，以及对困难或 无法测量的生理学; AIM 3-控制-扩展DA以包括以 期望的临床结果，例如，葡萄糖范围，并估计输入，例如，胰岛素或营养，需要 实现成果。