Towards enabling a cardiovascular digital twin for human systemic circulation using inverse analysis
- PDF / 2,016,646 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 85 Downloads / 175 Views
ORIGINAL PAPER
Towards enabling a cardiovascular digital twin for human systemic circulation using inverse analysis Neeraj Kavan Chakshu1 · Igor Sazonov1 · Perumal Nithiarasu1 Received: 28 March 2020 / Accepted: 29 September 2020 © The Author(s) 2020
Abstract An exponential rise in patient data provides an excellent opportunity to improve the existing health care infrastructure. In the present work, a method to enable cardiovascular digital twin is proposed using inverse analysis. Conventionally, accurate analytical solutions for inverse analysis in linear problems have been proposed and used. However, these methods fail or are not efficient for nonlinear systems, such as blood flow in the cardiovascular system (systemic circulation) that involves high degree of nonlinearity. To address this, a methodology for inverse analysis using recurrent neural network for the cardiovascular system is proposed in this work, using a virtual patient database. Blood pressure waveforms in various vessels of the body are inversely calculated with the help of long short-term memory (LSTM) cells by inputting pressure waveforms from three non-invasively accessible blood vessels (carotid, femoral and brachial arteries). The inverse analysis system built this way is applied to the detection of abdominal aortic aneurysm (AAA) and its severity using neural networks. Keywords Inverse analysis · Deep learning · Digital twin technology · Systemic circulation · Blood flow · Aneurysm detection
1 Introduction Data-driven analysis and monitoring are key drivers for the evolution of state-of-the-art health care. With increase in patients requiring medical care (Baker 2020), data generation and accumulation is also increasing at an alarming rate (Dinov 2016). This increase has put additional stress on an already challenging medical cyber-infrastructure. In addition to data accumulation, increase in number of patients is also causing unprecedented delays in critical care, as a result of rise in waiting lists. It is also important to note that late diagnosis is a significant reason for medical complications. Since a significant number of diagnosing and monitoring tools employed in critical care are invasive in nature, timeconsuming, expensive and labour-intensive, rise in these delays has become inevitable. This has given rise to a need for alternative but robust diagnosis and monitoring tools that can non-invasively detect medical conditions or diseases and * Perumal Nithiarasu [email protected] 1
Biomedical Engineering Group, Zienkiewicz Centre for Computational Engineering, College of Engineering, Swansea University, Swansea SA2 8PP, UK
help to monitor them with minimal amount of data. A potential key towards development of such tools is artificial intelligence, owing to its capacity to perform complex analyses. With recent advancements in artificial intelligence, especially in the area of deep learning, medical applications are being extensively developed with the help of neural networks and other deep learning algorithms. M
Data Loading...
