Mechanistic Machine Learning

机械机器学习

• 批准号: 9767278
• 负责人: David J. Albers
• 金额: $ 66.06万
• 依托单位: UNIVERSITY OF COLORADO DENVER
• 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 2022-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9767278
• 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; 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; optimal treatments; outcome forecast; outcome prediction; personalized learning; personalized medicine; physiologic model; predictive modeling; 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.

项目摘要 /摘要 该项目的目的是将经验数据与机械生理知识相结合以产生 个性化的定量预测，可以改善治疗方法。在正常实践中，医生 通过一般生理原理类比的原因，但是该技术的存在是为了利用甚至不完美 生理模型使治疗个性化和定量基础在生理学中，并改善 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，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使用非常有限 在医学上，通常应用于富含数据的情况，例如连续的葡萄糖监测或包装制造商。 我们以前的工作表明，使用葡萄糖 - 胰岛素模型的数据同化来预测葡萄糖 门诊2型糖尿病设置。我们将使用例如 限制的合奏Kalman滤波器和离线马尔可夫链蒙特卡洛算法，以更好地处理 在快速变化的患者上稀疏，短暂的训练集，我们将其应用于葡萄糖 重症监护室（ICU）的管理。此外，我们将开发用于表型应用的DA 利用DA的参数估计功能。数据同化可用于估计可测量 以及不可衡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，我们将开发一种方法 可能会概括，从更广泛地开始在医疗保健的背景下开发DA的努力。工作 我们提出的是能够使用机构驱动的DA进行测试，验证和优化的必要步骤 个性化的短期治疗策略，长期健康预测和机械生理学 理解。 我们将执行以下目标：AIM 1 -FORECAST-扩展了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 生理结果； AIM 2 - 表型 - 将DA框架扩展到陈述和参数估计到 允许基于机制的表型，仔细的不确定性定量以及难度的推断或 不可能衡量的生理学； AIM 3 - 控制 - 将DA扩展为包括一个以开始的控制器 所需的临床结果，例如葡萄糖范围，并估计输入，例如胰岛素或营养，需要 达到结果。

项目成果

Clinical Decision Support for Traumatic Brain Injury: Identifying a Framework for Practical Model-Based Intracranial Pressure Estimation at Multihour Timescales.

• DOI: 10.2196/23215
• 发表时间: 2021-03-22
• 期刊: JMIR medical informatics
• 影响因子: 3.2
• 作者: Stroh JN;Bennett TD;Kheyfets V;Albers D
• 通讯作者: Albers D

Personalization and Pragmatism: Pediatric Intracranial Pressure and Cerebral Perfusion Pressure Treatment Thresholds.

• DOI: 10.1097/pcc.0000000000002637
• 发表时间: 2021-02-01
• 期刊: Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies
• 作者: Stroh JN;Albers DJ;Bennett TD
• 通讯作者: Bennett TD

Neural Networks for Mortality Prediction: Ready for Prime Time?

• DOI: 10.1097/pcc.0000000000002710
• 发表时间: 2021-06-01
• 期刊: Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies
• 作者: Bennett TD;Russell S;Albers DJ
• 通讯作者: Albers DJ

Reduced model for female endocrine dynamics: Validation and functional variations.

女性内分泌动力学的简化模型：验证和功能变化。

• DOI: 10.1016/j.mbs.2023.108979
• 发表时间: 2023
• 期刊: Mathematical biosciences
• 影响因子: 4.3
• 作者: Graham,EricaJ;Elhadad,Noémie;Albers,David
• 通讯作者: Albers,David