Quantitative, Model-based Medical Decision support by Bayesian Inference

通过贝叶斯推理支持基于模型的定量医疗决策

• 批准号: 7658616
• 负责人: Gilles Clermont
• 金额: $ 23.14万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-08-01 至 2011-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/7658616
• 关键词: Acute; Adverse event; Algorithms; Bolus Infusion; Cardiac Output; Cardiovascular system; Caring; Clinical; Computer software; Critical Care; Critical Illness; Data; Data Set; Databases; Decision Making; Development; Diagnosis; Diagnostic; Differential Diagnosis; Drug Formulations; Environment; Exhibits; Functional disorder; Goals; Hypotension; Imaging technology; Individual; Intensive Care Units; Intervention; Knowledge; Laboratories; Liquid substance; Maps; Markov Chains; Measurement; Medical; Medicine; Methodology; Methods; Modeling; Monitor; Outcome; Patients; Physiological; Physiology; Probability; Procedures; Process; Quantitative Evaluations; Research; Research Infrastructure; Simulate; Solutions; Structure; Technology; Therapeutic; Time; Translating; Uncertainty; Validation; Variant; base; cohort; computerized; data acquisition; density; improved; mathematical model; meetings; novel; novel strategies; parallel computing; programs; public health relevance; response; simulation; tool; vector

DESCRIPTION (provided by applicant): The amount of quantitative data available to the clinician at the bedside, in particular in data-rich environments such as the intensive care unit (ICU), has grown tremendously due to advances in medical monitoring and imaging technology. Yet, these advances have largely failed to improve outcomes and significantly impact medical decision making by bedside clinicians, particularly in the acute care setting. Computerized decision support technologies based on quantitative, mechanistic mathematical models of physiology might help alleviate this situation. Their application, however, has been hindered by the fundamental difficulties encountered when solving the inverse problem of finding model parameters and states best compatible with the observations in individual patients. We have recently shown in a simplified simulation setting how Bayesian inference may use such models to quantitatively interpret clinical measurements and observations, and eventually predict the result of acute interventions and optimize therapy in individual patients. Rather than attempting to find a single, best parameter vector, we compute the full posterior probability distributions of parameters and states of a mechanistic model conditional on the available data. These distributions integrate uncertainty arising from measurement error and the fundamental non- uniqueness of the solution of the underlying parameter/state estimation problem, and translate into physiologically meaningful probabilistic, yet quantitative interpretations of clinical measurements. We have shown that a direct mapping between the multimodal structure of the inferred distributions representing estimated patient condition and the clinical concept of differential diagnoses may exist. The overarching goal of the program outlined in this proposal is to explore the practical usefulness of this novel approach in a cohort of critically ill patients. The proposed research plan will focus on cardiovascular pathophysiology, with the objectives of (1) using mathematical models to provide quantitative estimates of patient condition that incorporate more of the routinely acquired high density data than can be processed by the clinician, (2) formally validating the accuracy and predictive power of these estimates. It will thus provide a first quantitative evaluation of the potential usefulness of this approach as a quantitative, physiology based decision support tool in critical care medicine. PUBLIC HEALTH RELEVANCE: Clinical decision making and clinical outcomes have not benefitted from the large increase in availability of quantitative data collected at the bedside and in the laboratory. This proposal suggests the development of an entirely novel bedside computerized decision support technology that interprets data flow based on quantitative, mechanistic mathematical models of physiology. Such a tool might be of great assistance to clinicians in integrating this dynamic flow of information in the formulation of diagnoses and optimally informed therapeutic strategies.

描述（由申请人提供）：由于医学监测和成像技术的进步，临床医生在床边可用的定量数据量，特别是在数据丰富的环境中，如重症监护室（ICU），已经大幅增长。然而，这些进展在很大程度上未能改善结果，并显著影响床旁临床医生的医疗决策，特别是在急性护理环境中。基于生理学的定量、机械数学模型的计算机化决策支持技术可能有助于缓解这种情况。然而，他们的应用程序，已受到阻碍的基本困难时遇到的逆问题，找到模型参数和状态最好的兼容在个别患者的观察。我们最近在一个简化的模拟环境中展示了贝叶斯推理如何使用这些模型来定量解释临床测量和观察结果，并最终预测急性干预的结果并优化个体患者的治疗。而不是试图找到一个单一的，最好的参数向量，我们计算的参数和状态的机械模型的条件下的可用数据的完整的后验概率分布。这些分布整合了由测量误差和基本参数/状态估计问题的解的基本非唯一性引起的不确定性，并且转化为临床测量的生理上有意义的概率性但定量的解释。我们已经表明，一个直接的映射之间的多模态结构的推断分布代表估计患者的病情和临床概念的鉴别诊断可能存在。本提案中概述的该计划的总体目标是探索这种新方法在危重患者队列中的实用性。拟议的研究计划将侧重于心血管病理生理学，其目标是（1）使用数学模型提供患者状况的定量估计，其中包含比临床医生可以处理的更多的常规采集的高密度数据，（2）正式验证这些估计的准确性和预测能力。因此，它将提供第一个定量评估的潜在有用性，这种方法作为一个定量的，基于生理学的决策支持工具，在重症监护医学。 公共卫生相关性：临床决策和临床结果并没有从床边和实验室收集的定量数据的大量增加中受益。该提案建议开发一种全新的床边计算机化决策支持技术，该技术基于生理学的定量、机械数学模型来解释数据流。这样的工具可能是很大的帮助，临床医生在制定诊断和最佳知情的治疗策略，整合这种动态的信息流。