Computational Analysis of Hemodynamic Indices Based on Personalized Identification of Aortic Pulse Wave Velocity by a Neural Network

Timur Gamilov; Fuyou Liang; Philipp Kopylov; Natalia Kuznetsova; Artem Rogov; Sergey Simakov

doi:10.3390/math11061358

journal article Open Access Mar 10, 2023

Computational Analysis of Hemodynamic Indices Based on Personalized Identification of Aortic Pulse Wave Velocity by a Neural Network

Timur Gamilov

Fuyou Liang

Philipp Kopylov

Natalia Kuznetsova

Artem Rogov Sergey Simakov

Mathematics Vol. 11 No. 6 pp. 1358 · MDPI AG

View at Publisher Save 10.3390/math11061358

Abstract

Adequate personalized numerical simulation of hemodynamic indices in coronary arteries requires accurate identification of the key parameters. Elastic properties of coronary vessels produce a significant effect on the accuracy of simulations. Direct measurements of the elasticity of coronary vessels are not available in the general clinic. Pulse wave velocity (AoPWV) in the aorta correlates with aortic and coronary elasticity. In this work, we present a neural network approach for estimating AoPWV. Because of the limited number of clinical cases, we used a synthetic AoPWV database of virtual subjects to train the network. We use an additional set of AoPWV data collected from real patients to test the developed algorithm. The developed neural network predicts brachial–ankle AoPWV with a root-mean-square error (RMSE) of 1.3 m/s and a percentage error of 16%. We demonstrate the relevance of a new technique by comparing invasively measured fractional flow reserve (FFR) with simulated values using the patient data with constant (7.5 m/s) and predicted AoPWV. We conclude that patient-specific identification of AoPWV via the developed neural network improves the estimation of FFR from 4.4% to 3.8% on average, with a maximum difference of 2.8% in a particular case. Furthermore, we also numerically investigate the sensitivity of the most useful hemodynamic indices, including FFR, coronary flow reserve (CFR) and instantaneous wave-free ratio (iFR) to AoPWV using the patient-specific data. We observe a substantial variability of all considered indices for AoPWV below 10 m/s and weak variation of AoPWV above 15 m/s. We conclude that the hemodynamic significance of coronary stenosis is higher for the patients with AoPWV in the range from 10 to 15 m/s. The advantages of our approach are the use of a limited set of easily measured input parameters (age, stroke volume, heart rate, systolic, diastolic and mean arterial pressures) and the usage of a model-generated (synthetic) dataset to train and test machine learning methods for predicting hemodynamic indices. The application of our approach in clinical practice saves time, workforce and funds.

Topics

No keywords indexed for this article. Browse by subject →

References

53

[1]

Christiansen "Instantaneous wave-free ratio versus fractional flow reserve to guide PCI" N. Engl. J. Med. (2019)

[2]

Gould "Coronary flow reserve as a physiologic measure of stenosis severity" J. Am. Coll. Cardiol. (1990) 10.1016/s0735-1097(10)80078-6

[3]

Carson "Non-invasive coronary CT angiography-derived fractional flow reserve: A benchmark study comparing the diagnostic performance of four different computational methodologies" Int. J. Numer. Methods Biomed. Eng. (2019) 10.1002/cnm.3235

[4]

Carson "Computational instantaneous wave-free ratio (IFR) for patient-specific coronary artery stenoses using 1D network models" Int. J. Numer. Methods Biomed. Eng. (2019) 10.1002/cnm.3255

[5]

Simakov, S., Gamilov, T., Liang, F., and Kopylov, P. (2021). Computational analysis of haemodynamic indices in synthetic atherosclerotic coronary netwroks. Mathematics, 9. 10.20944/preprints202108.0026.v1

[6]

Gognieva "Noninvasive assessment of the fractional flow reserve with the CT FFRc 1D method: Final results of a pilot study" Glob. Heart (2020)

[7]

Zheng "A One-Dimensional Hemodynamic Model of the Coronary Arterial Tree" Front. Physiol. (2019) 10.3389/fphys.2019.00853

[8]

Mynard "Scalability and in vivo validation of a multiscale numerical model of the left coronary circulation" Am. J. Physiol. Heart Circ. (2014) 10.1152/ajpheart.00603.2013

[9]

Kamangar "Patient-specific 3D hemodynamics modelling of left coronary artery under hyperemic conditions" Med. Biol. Eng. Comput. (2017) 10.1007/s11517-016-1604-8

[10]

Lu "Noninvasive FFR Derived From Coronary CT Angiography: Management and Outcomes in the PROMISE Trial" JACC Cardiovasc. Imaging (2017) 10.1016/j.jcmg.2016.11.024

[11]

Charlton "Modeling arterial pulse waves in healthy aging: A database for in silico evaluation of hemodynamics and pulse wave indexes" Am. J.-Physiol.-Heart Circ. Physiol. (2019) 10.1152/ajpheart.00218.2019

[12]

Charlton, P.H. (2023, February 23). Pulse Wave Database. Available online: https://peterhcharlton.github.io/pwdb/pwdb.html.

[13]

Reavette "Comparison of arterial wave intensity analysis by pressure-velocity and diameter-velocity methods in a virtual population of adult subjects" Proc. Inst. Mech. Eng. H (2020) 10.1177/0954411920926094

[14]

Jones "A physiologically realistic virtual patient database for the study of arterial haemodynamics" Int. J. Numer. Method Biomed. Eng. (2021) 10.1002/cnm.3497

[15]

Wang, T., Jin, W., Liang, F., and Alastruey, J. (2021). Machine Learning–Based Pulse Wave Analysis for Early Detection of Abdominal Aortic Aneurysms Using In Silico Pulse Waves. Symmetry, 13. 10.20944/preprints202103.0745.v1

[16]

Carson "Artificial intelligence approaches to predict coronary stenosis severity using non-invasive fractional flow reserve" Proc. Inst. Mech. Eng. H (2020) 10.1177/0954411920946526

[17]

Fossan "Machine learning augmented reduced-order models for FFR-prediction" Comput. Methods Appl. Mech. Eng. (2021) 10.1016/j.cma.2021.113892

[18]

Danilov "Methods of graph network reconstruction in personalized medicine" Int. J. Numer. Methods Biomed. Eng. (2016) 10.1002/cnm.2754

[19]

Vassilevski "On the elasticity of blood vessels in one-dimensional problems of haemodynamics" Comput. Math. Math. Phys. (2015) 10.1134/s0965542515090134

[20]

Simakov "Numerical evaluation of the effectiveness of coronary revascularization" Russ. J. Num. Anal. Math. Mod. (2021) 10.1515/rnam-2021-0025

[21]

Matthys "Pulse wave propagation in a model human arterial network: Assessmentof 1D numerical simulations against in-vitro measurements" J. Biomech. (2007) 10.1016/j.jbiomech.2007.05.027

[22]

Milan "Current assessment of pulse wave velocity: Comprehensive review of validation studies" J. Hypertens. (2019) 10.1097/hjh.0000000000002081

[23]

Pereira "Novel Methods for Pulse Wave Velocity Measurement" J. Med. Biol. Eng. (2015) 10.1007/s40846-015-0086-8

[24]

Filip, C., Cirstoveanu, C., Bizubac, M., Berghea, E.C., Căpitănescu, A., Bălgrădean, M., Pavelescu, C., Nicolescu, A., and Ionescu, M.D. (2021). Pulse Wave Velocity as a Marker of Vascular Dysfunction and Its Correlation with Cardiac Disease in Children with End-Stage Renal Disease (ESRD). Diagnostics, 12. 10.3390/diagnostics12010071

[25]

Shahzad "Quantification of aortic pulse wave velocity from a population based cohort: A fully automatic method" J. Cardiovasc. Magn. Reson. (2019) 10.1186/s12968-019-0530-y

[26]

Dekkers "Normal and reference values for cardiovascular magnetic resonance-based pulse wave velocity in the middle-aged general population" J. Cardiovasc. Magn. Reson. (2021) 10.1186/s12968-021-00739-y

[27]

Aguado-Sierra, J., Parke, K.H., Davies, J.E., Francis, D., Hughes, A.D., and Mayet, J. (September, January 30). Arterial pulse wave velocity in coronary arteries. Proceedings of the 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, New York, NY, USA. 10.1109/iembs.2006.259375

[28]

Harbaoui "Development of Coronary Pulse Wave Velocity: New Pathophysiological Insight Into Coronary Artery Disease" J. Am. Heart Assoc. (2017) 10.1161/jaha.116.004981

[29]

Barret, K., Brooks, H., Boitano, S., and Barman, S. (2010). Ganong’s Review of Medical Physiology, The McGraw-Hill. [23rd ed.].

[30]

Gamilov, T., Kopylov, P., Serova, M., Syunaev, R., Pikunov, A., Belova, S., Liang, F., Alastruey, J., and Simakov, S. (2020). Computational analysis of coronary blood flow: The role of asynchronous pacing and arrhythmias. Mathematics, 8. 10.3390/math8081205

[31]

Magomedov, K.M., and Kholodov, A.S. (2018). Grid–Characteristic Numerical Methods, Nauka. (In Russian).

[32]

Ernest "On outflow boundary conditions for CT-based computation of FFR: Examination using PET images" Med. Eng. Phys. (2020) 10.1016/j.medengphy.2019.10.007

[33]

Pijls "Measurement of Fractional Flow Reserve to Assess the Functional Severity of Coronary-Artery Stenoses" N. Engl. J. Med. (1996) 10.1056/nejm199606273342604

[34]

Nijjer "Improvement in coronary haemodynamics after percutaneous coronary intervention: Assessment using instantaneous wave-free ratio" Heart (2013) 10.1136/heartjnl-2013-304387

[35]

Sen "Development and validation of a new adenosine–independent index of stenosis severity from coronary wave-intensity analysis: Results of the ADVISE (ADenosine Vasodilator Independent Stenosis Evaluation) study" J. Am. Coll. Cardiol. (2012) 10.1016/j.jacc.2011.11.003

[36]

Carson, J., Pant, S., Roobottom, C., Alcock, R., Blanco, P.J., Bulant, C.A., Vassilevski, Y., Simakov, S., Gamilov, T., and Pryamonosov, R. (2023, February 23). Supplementary Material. 2019. Available online: https://doi.org/10.6084/m9.figshare.8047742.v2.

[37]

Laurent "Aortic stiffness is an independent predictor of all-cause and cardiovascular mortality in hypertensive patients" Hypertension (2001) 10.1161/01.hyp.37.5.1236

[38]

Munakata "Brachial-Ankle Pulse Wave Velocity: Background, Method, and Clinical Evidence" Pulse (2016) 10.1159/000443740

[39]

Collis "Relations of stroke volume and cardiac output to body composition: The strong heart study" Circulation (2001) 10.1161/01.cir.103.6.820

[40]

Deep learning in neural networks: An overview

Jürgen Schmidhuber

Neural Networks 2015 10.1016/j.neunet.2014.09.003

[41]

Grillo "Short-Term Repeatability of Noninvasive Aortic Pulse Wave Velocity Assessment: Comparison Between Methods and Devices" Am. J. Hypertens. (2018) 10.1093/ajh/hpx140

[42]

Yamashina "Validity, reproducibility, and clinical significance of noninvasive brachial-ankle pulse wave velocity measurement" Hypertens. Res. (2002) 10.1291/hypres.25.359

[43]

Kang "Relationship between brachial-ankle pulse wave velocity and invasively measured aortic pulse pressure" J. Clin. Hypertens. (2018) 10.1111/jch.13200

[44]

Sugawara "Brachial–ankle pulse wave velocity: An index of central arterial stiffness?" J. Hum. Hypertens (2005) 10.1038/sj.jhh.1001838

[45]

Mahesh "Machine Learning Algorithms—A Review" Int. J. Sci. Res. (2020)

[46]

An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization

Thomas G. Dietterich

Machine Learning 2000 10.1023/a:1007607513941

[47]

Rossi "Aortic stiffness: An old concept for new insights into the pathophysiology of functional mitral regurgitation" Heart Vessel. (2013) 10.1007/s00380-012-0295-9

[48]

Jin, W., Chowienczyk, P., and Alastruey, J. (2021). Estimating pulse wave velocity from the radial pressure wave using machine learning algorithms. PLoS ONE, 16. 10.1371/journal.pone.0245026

[49]

Dekkers "Estimated pulse wave velocity (ePWV) as a potential gatekeeper for MRI-assessed PWV: A linear and deep neural network based approach in 2254 participants of the Netherlands Epidemiology of Obesity study" Int. J. Cardiovasc. Imaging (2022) 10.1007/s10554-021-02359-0

[50]

Tavallali "Artificial Intelligence Estimation of Carotid-Femoral Pulse Wave Velocity using Carotid Waveform" Sci. Rep. (2018) 10.1038/s41598-018-19457-0

Showing 50 of 53 references

Cited By

6

Validation of boundary conditions for coronary circulation model based on a lumped parameter approach

Sergey S. Simakov, Timur M. Gamilov · 2023

Russian Journal of Numerical Analys...

Metrics

6

Citations

53

References

Details

Published: Mar 10, 2023
Vol/Issue: 11(6)
Pages: 1358
License: View

Authors

T

Timur Gamilov

Marchuk Institute of Numerical Mathematics of the Russian Academy of Sciences, 119991 Moscow, Russia; Moscow Institute of Physics and Technology, 141701 Dolgoprudny, Russia; World-Class Research Center “Digital Biodesign and Personalized Healthcare”, Sechenov First Moscow State Medical University, 19991 Moscow, Russia; Department of Mathematical Modelling of Processes and Materials, Sirius University of Science and Technology, 354340 Sochi, Russia

F

Fuyou Liang

World-Class Research Center “Digital Biodesign and Personalized Healthcare”, Sechenov First Moscow State Medical University, 19991 Moscow, Russia; Department of Engineering Mechanics, School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

P

Philipp Kopylov

World-Class Research Center “Digital Biodesign and Personalized Healthcare”, Sechenov First Moscow State Medical University, 19991 Moscow, Russia

N

Natalia Kuznetsova

World-Class Research Center “Digital Biodesign and Personalized Healthcare”, Sechenov First Moscow State Medical University, 19991 Moscow, Russia

A

Artem Rogov

Moscow Institute of Physics and Technology, 141701 Dolgoprudny, Russia; World-Class Research Center “Digital Biodesign and Personalized Healthcare”, Sechenov First Moscow State Medical University, 19991 Moscow, Russia

S

Sergey Simakov

Marchuk Institute of Numerical Mathematics of the Russian Academy of Sciences, 119991 Moscow, Russia; Moscow Institute of Physics and Technology, 141701 Dolgoprudny, Russia; Institute of Computer Sciences and Mathematical Modelling, Sechenov University, 119992 Moscow, Russia

Funding

National Natural Science Foundation of China Award: 21–41–00029

Russian Science Foundation Award: 21–41–00029

Cite This Article

Timur Gamilov, Fuyou Liang, Philipp Kopylov, et al. (2023). Computational Analysis of Hemodynamic Indices Based on Personalized Identification of Aortic Pulse Wave Velocity by a Neural Network. Mathematics, 11(6), 1358. https://doi.org/10.3390/math11061358

Computational Analysis of Hemodynamic Indices Based on Personalized Identification of Aortic Pulse Wave Velocity by a Neural Network

You May Also Like