Collaborative Research: Physical-Statistical Modeling and Optimization of Cardiovascular System

合作研究：心血管系统的物理统计建模和优化

• 批准号: 1266025
• 负责人: Roshan Joseph
• 金额: $ 15万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-08-01 至 2017-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1266025&HistoricalAwards=false
• 关键词: Collaborative; Research; Physical; Statistical; Modeling

The objective of this collaborative research project is to develop physical-statistical models of cardiovascular systems for optimizing medical decision making in spatiotemporal disease processes. Multi-scale computer models will be developed to improve the understanding of disease-altered cardiac electrical dynamics. In particular, the modeling will be done in multiple physical levels starting with ion channels, then cells, then tissues, and finally an anatomically realistic heart. Physics-based models will be statistically calibrated and adjusted so as to make more realistic predictions. Furthermore, an easy-to-evaluate statistical surrogate model will be developed for faster approximation, prediction and optimization, thereby facilitating real-time medical decision making. Physical-statistical models will be used in conjunction with sensor-based data fusion to optimize cardiovascular diagnostics. The simulation-based optimization approach provides a unique opportunity to search the optimal medical decisions with the "virtual" heart, as opposed to traditional "experience-based", "trial-and-error" or subjective decisions in the real-world heart. If successful, the results of this research will yield a fundamental understanding of the progression of cardiac diseases that is so vitally needed to improve preventive healthcare services. This research has the potential to make a paradigm shift in healthcare, i.e., from reactive care to preventive and proactive care, from experience-based to evidence-based cardiac care services. The early identification of cardiovascular diseases will decrease mortality rates, promote the timely delivery of life-saving interventions, and reduce healthcare cost (e.g., preventive care in lieu of expensive surgical interventions). This will positively impact cardiovascular patients, the largest population at risk of death in the US and in the world. This project will provide students with a unique opportunity to obtain multidisciplinary training in industrial and systems engineering, healthcare, statistics and optimization.

该合作研究项目的目标是开发心血管系统的物理统计模型，以优化时空疾病过程中的医疗决策。将开发多尺度计算机模型，以提高对疾病改变的心脏电动力学的理解。特别是，建模将在多个物理层面上完成，从离子通道开始，然后是细胞，然后是组织，最后是解剖学上逼真的心脏。将对基于物理的模型进行统计校准和调整，以便作出更切合实际的预测。此外，还将开发一种易于评估的统计替代模型，以便更快地进行近似、预测和优化，从而促进实时医疗决策。物理统计模型将与基于传感器的数据融合结合使用，以优化心血管诊断。基于模拟的优化方法提供了一个独特的机会，以搜索最佳的医疗决策与“虚拟”的心脏，而不是传统的“基于经验的”，“试错”或主观的决定在现实世界的心脏。如果成功，这项研究的结果将产生对心脏疾病进展的基本了解，这对于改善预防性医疗服务至关重要。这项研究有可能在医疗保健领域实现范式转变，即，从反应性护理到预防性和主动性护理，从基于经验的心脏护理服务到基于证据的心脏护理服务。早期发现心血管疾病将降低死亡率，促进及时提供救生干预措施，并降低医疗保健成本（例如，预防性护理代替昂贵的手术干预）。这将对心血管患者产生积极影响，心血管患者是美国和世界上最大的死亡风险人群。该项目将为学生提供一个独特的机会，获得工业和系统工程，医疗保健，统计和优化多学科培训。