A data-driven framework to identify restenosis-prone regions in femoral arteries from geometric and inflow waveform parameters
Journal of the Royal Society Interface · 2026
DOI: 10.1098/rsif.2026.0109 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Royal Society Interface, 2026. Verfasst von Chotirawee Chatpattanasiri und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, University College London , London, UK. Hauptthemen laut MEDLINE: Femoral Artery, Models, Cardiovascular, Peripheral Arterial Disease, Machine Learning. Die Arbeit nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hawkes Institute, University College London EPSRC Centre for Doctoral Training i4health, EPSRC Research.
Abstract (Originalsprache)
Haemodynamic indices derived from computational fluid dynamics (CFD), such as time-averaged wall shear stress (TAWSS) and oscillatory shear index (OSI), are closely associated with restenosis risk in peripheral arterial disease (PAD). We present a machine learning–reduced order modelling (ML-ROM) framework to predict critical, restenosis-prone, haemodynamic regions accounting for both vessel geometries and inlet flow waveforms. We generated 500 parameterized virtual femoral-artery geometries, each paired with a synthetic physiologically realistic inflow waveform. CFD was used to obtain the wall shear stress (WSS) distribution, from which TAWSS and OSI were computed. Critical regions were then defined by applying different thresholding criteria based on TAWSS and OSI, as found in the literature. These were then used to construct ROMs using Proper Orthogonal Decomposition (POD), and to train ML models from which the critical regions could be reconstructed. Four ML architectures were explored: a geometric-parameter-only model and three alternatives that also incorporate inflow waveform information via Fourier coefficients, long short-term memory (LSTM), and convolutional neural networks (CNN). The Fourier models achieved the highest predictive performance, with the median values of balanced accuracy (BA) exceeding 0.92 across all critical-region definitions. The model also offered a substantial speed-up ratio of the order of 109 compared with traditional CFD.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mechanical Engineering, University College London , London, UK.
- UCL Hawkes Institute, University College London , London, UK.
- Department of Medical Physics and Biomedical Engineering, University College London , London, UK.
ORCID-Profile: Chotirawee Chatpattanasiri, Federica Ninno, Vanessa Diaz-Zuccarini, Stavroula Balabani
Förderung
- Hawkes Institute
- University College London EPSRC Centre for Doctoral Training i4health
- EPSRC Research
- BBSRC Internal Institutional Awards University College London
- AWS Doctoral Scholarship in Digital Innovation
- Department of Mechanical Engineering, University College London
Zitieren
APA
Chatpattanasiri, C., Ninno, F., Diaz-Zuccarini, V., & Balabani, S. (2026). A data-driven framework to identify restenosis-prone regions in femoral arteries from geometric and inflow waveform parameters. Journal of the Royal Society Interface. https://doi.org/10.1098/rsif.2026.0109
Vancouver
Chatpattanasiri C, Ninno F, Diaz-Zuccarini V, Balabani S. A data-driven framework to identify restenosis-prone regions in femoral arteries from geometric and inflow waveform parameters. Journal of the Royal Society Interface. 2026. doi:10.1098/rsif.2026.0109
BibTeX
@article{Chatpattanasiri2026,
author = {Chatpattanasiri, Chotirawee and Ninno, Federica and Diaz-Zuccarini, Vanessa and Balabani, Stavroula},
title = {A data-driven framework to identify restenosis-prone regions in femoral arteries from geometric and inflow waveform parameters},
journal = {Journal of the Royal Society Interface},
year = {2026},
doi = {10.1098/rsif.2026.0109}
}
EUVIMED