Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield S10 2TN, UK; Department of Circulation and Medical Imaging, Norwegian University of Science and Technology (NTNU), Trondheim, Norway; Insigneo Institute for in silico Medicine, University of Sheffield, Sheffield, UK.
Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield S10 2TN, UK; Insigneo Institute for in silico Medicine, University of Sheffield, Sheffield, UK.
Med Eng Phys. 2019 Oct;72:38-48. doi: 10.1016/j.medengphy.2019.08.007.
The aim of this position paper is to provide a brief overview of the current status of cardiovascular modelling and of the processes required and some of the challenges to be addressed to see wider exploitation in both personal health management and clinical practice. In most branches of engineering the concept of the digital twin, informed by extensive and continuous monitoring and coupled with robust data assimilation and simulation techniques, is gaining traction: the Gartner Group listed it as one of the top ten digital trends in 2018. The cardiovascular modelling community is starting to develop a much more systematic approach to the combination of physics, mathematics, control theory, artificial intelligence, machine learning, computer science and advanced engineering methodology, as well as working more closely with the clinical community to better understand and exploit physiological measurements, and indeed to develop jointly better measurement protocols informed by model-based understanding. Developments in physiological modelling, model personalisation, model outcome uncertainty, and the role of models in clinical decision support are addressed and 'where-next' steps and challenges discussed.
本文旨在简要概述心血管建模的现状，以及在个人健康管理和临床实践中广泛应用所需的过程和一些需要解决的挑战。在工程学的大多数领域，数字孪生的概念正在得到越来越多的关注，这一概念通过广泛而持续的监测来实现，并结合了强大的数据同化和模拟技术：高德纳集团（Gartner Group）将其列为 2018 年十大数字趋势之一。心血管建模领域正在开始采用更系统的方法来结合物理学、数学、控制理论、人工智能、机器学习、计算机科学和先进的工程方法，同时与临床社区更紧密地合作，以更好地理解和利用生理测量，并根据基于模型的理解共同制定更好的测量协议。本文还讨论了生理建模、模型个性化、模型结果不确定性以及模型在临床决策支持中的作用等方面的发展，并探讨了下一步的发展方向和挑战。
