ML-ROM wall shear stress prediction in patient-specific vascular pathologies under a limited clinical training data regime.

High-fidelity numerical simulations such as Computational Fluid Dynamics (CFD) have been proven effective in analysing haemodynamics, offering insight into many vascular conditions. However, these methods often face challenges of high computational cost and long processing times. Data-driven approac...

Full description

Saved in:
Bibliographic Details
Main Authors: Chotirawee Chatpattanasiri, Federica Ninno, Catriona Stokes, Alan Dardik, David Strosberg, Edouard Aboian, Hendrik von Tengg-Kobligk, Vanessa Díaz-Zuccarini, Stavroula Balabani
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0325644
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849694314658004992
author Chotirawee Chatpattanasiri
Federica Ninno
Catriona Stokes
Alan Dardik
David Strosberg
Edouard Aboian
Hendrik von Tengg-Kobligk
Vanessa Díaz-Zuccarini
Stavroula Balabani
author_facet Chotirawee Chatpattanasiri
Federica Ninno
Catriona Stokes
Alan Dardik
David Strosberg
Edouard Aboian
Hendrik von Tengg-Kobligk
Vanessa Díaz-Zuccarini
Stavroula Balabani
author_sort Chotirawee Chatpattanasiri
collection DOAJ
description High-fidelity numerical simulations such as Computational Fluid Dynamics (CFD) have been proven effective in analysing haemodynamics, offering insight into many vascular conditions. However, these methods often face challenges of high computational cost and long processing times. Data-driven approaches such as Reduced Order Modeling (ROM) and Machine Learning (ML) are increasingly being explored alongside CFD to advance biomechanical research and application. This study presents an integration of Proper Orthogonal Decomposition (POD)-based ROM with neural network-based ML models to predict Wall Shear Stress (WSS) in patient-specific vascular pathologies. CFD was used to generate WSS data, followed by POD to construct the ROM. The ML models were trained to predict the ROM coefficients from the inlet flowrate waveform, which can be routinely collected in the clinic. Two ML models were explored: a simpler flowrate-coefficients mapping model and a more advanced autoregressive model. Both models were tested against two case studies: flow in Peripheral Arterial Disease (PAD) and flow in Aortic Dissection (AD). Despite the limited training data sets (three flowrate waveforms for the PAD case and two for the AD case), the models were able to predict the haemodynamic indices, with the flowrate-coefficients mapping model outperforming the autoregressive model in both case studies. The accuracy is higher in the PAD case study, with reduced accuracy in the more complex case study of AD. Additionally, the computational cost analysis reveals a significant reduction in computational demands, with speed-up ratios in the order of 104 for both case studies. This approach shows an effective integration of ROM and ML techniques for fast and reliable evaluations of haemodynamic properties that contribute to vascular conditions, setting the stage for clinical translation.
format Article
id doaj-art-0aa14c93824543c69b0c4eef7ef45b53
institution DOAJ
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-0aa14c93824543c69b0c4eef7ef45b532025-08-20T03:20:09ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01206e032564410.1371/journal.pone.0325644ML-ROM wall shear stress prediction in patient-specific vascular pathologies under a limited clinical training data regime.Chotirawee ChatpattanasiriFederica NinnoCatriona StokesAlan DardikDavid StrosbergEdouard AboianHendrik von Tengg-KobligkVanessa Díaz-ZuccariniStavroula BalabaniHigh-fidelity numerical simulations such as Computational Fluid Dynamics (CFD) have been proven effective in analysing haemodynamics, offering insight into many vascular conditions. However, these methods often face challenges of high computational cost and long processing times. Data-driven approaches such as Reduced Order Modeling (ROM) and Machine Learning (ML) are increasingly being explored alongside CFD to advance biomechanical research and application. This study presents an integration of Proper Orthogonal Decomposition (POD)-based ROM with neural network-based ML models to predict Wall Shear Stress (WSS) in patient-specific vascular pathologies. CFD was used to generate WSS data, followed by POD to construct the ROM. The ML models were trained to predict the ROM coefficients from the inlet flowrate waveform, which can be routinely collected in the clinic. Two ML models were explored: a simpler flowrate-coefficients mapping model and a more advanced autoregressive model. Both models were tested against two case studies: flow in Peripheral Arterial Disease (PAD) and flow in Aortic Dissection (AD). Despite the limited training data sets (three flowrate waveforms for the PAD case and two for the AD case), the models were able to predict the haemodynamic indices, with the flowrate-coefficients mapping model outperforming the autoregressive model in both case studies. The accuracy is higher in the PAD case study, with reduced accuracy in the more complex case study of AD. Additionally, the computational cost analysis reveals a significant reduction in computational demands, with speed-up ratios in the order of 104 for both case studies. This approach shows an effective integration of ROM and ML techniques for fast and reliable evaluations of haemodynamic properties that contribute to vascular conditions, setting the stage for clinical translation.https://doi.org/10.1371/journal.pone.0325644
spellingShingle Chotirawee Chatpattanasiri
Federica Ninno
Catriona Stokes
Alan Dardik
David Strosberg
Edouard Aboian
Hendrik von Tengg-Kobligk
Vanessa Díaz-Zuccarini
Stavroula Balabani
ML-ROM wall shear stress prediction in patient-specific vascular pathologies under a limited clinical training data regime.
PLoS ONE
title ML-ROM wall shear stress prediction in patient-specific vascular pathologies under a limited clinical training data regime.
title_full ML-ROM wall shear stress prediction in patient-specific vascular pathologies under a limited clinical training data regime.
title_fullStr ML-ROM wall shear stress prediction in patient-specific vascular pathologies under a limited clinical training data regime.
title_full_unstemmed ML-ROM wall shear stress prediction in patient-specific vascular pathologies under a limited clinical training data regime.
title_short ML-ROM wall shear stress prediction in patient-specific vascular pathologies under a limited clinical training data regime.
title_sort ml rom wall shear stress prediction in patient specific vascular pathologies under a limited clinical training data regime
url https://doi.org/10.1371/journal.pone.0325644
work_keys_str_mv AT chotiraweechatpattanasiri mlromwallshearstresspredictioninpatientspecificvascularpathologiesunderalimitedclinicaltrainingdataregime
AT federicaninno mlromwallshearstresspredictioninpatientspecificvascularpathologiesunderalimitedclinicaltrainingdataregime
AT catrionastokes mlromwallshearstresspredictioninpatientspecificvascularpathologiesunderalimitedclinicaltrainingdataregime
AT alandardik mlromwallshearstresspredictioninpatientspecificvascularpathologiesunderalimitedclinicaltrainingdataregime
AT davidstrosberg mlromwallshearstresspredictioninpatientspecificvascularpathologiesunderalimitedclinicaltrainingdataregime
AT edouardaboian mlromwallshearstresspredictioninpatientspecificvascularpathologiesunderalimitedclinicaltrainingdataregime
AT hendrikvontenggkobligk mlromwallshearstresspredictioninpatientspecificvascularpathologiesunderalimitedclinicaltrainingdataregime
AT vanessadiazzuccarini mlromwallshearstresspredictioninpatientspecificvascularpathologiesunderalimitedclinicaltrainingdataregime
AT stavroulabalabani mlromwallshearstresspredictioninpatientspecificvascularpathologiesunderalimitedclinicaltrainingdataregime