{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:09:21Z","timestamp":1792786161820,"version":"4.5.0"},"reference-count":77,"publisher":"The Royal Society","issue":"243","license":[{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"vor","delay-in-days":7,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hawkes Institute"},{"name":"University College London EPSRC Centre for Doctoral Training i4health","award":["EP\/S021930\/1"],"award-info":[{"award-number":["EP\/S021930\/1"]}],"id":[{"id":"https:\/\/ror.org\/02jx3x895","id-type":"ROR","asserted-by":"crossref"}]},{"name":"EPSRC Research","award":["EP\/W00481X\/1"],"award-info":[{"award-number":["EP\/W00481X\/1"]}]},{"name":"BBSRC Internal Institutional Awards University College London","id":[{"id":"https:\/\/ror.org\/02jx3x895","id-type":"ROR","asserted-by":"crossref"}]},{"name":"AWS Doctoral Scholarship in Digital Innovation"},{"name":"Department of Mechanical Engineering, University College London","id":[{"id":"https:\/\/ror.org\/02jx3x895","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>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\u2013reduced 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.<\/jats:p>","DOI":"10.1098\/rsif.2026.0109","type":"journal-article","created":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:09:37Z","timestamp":1791936577000},"source":"Crossref","is-referenced-by-count":0,"title":["A data-driven framework to identify restenosis-prone regions in femoral arteries from geometric and inflow waveform parameters"],"prefix":"10.1098","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1721-3806","authenticated-orcid":false,"given":"Chotirawee","family":"Chatpattanasiri","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, University College London 1 , London, UK"},{"name":"UCL Hawkes Institute, University College London 2 , London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8497-1079","authenticated-orcid":false,"given":"Federica","family":"Ninno","sequence":"additional","affiliation":[{"name":"UCL Hawkes Institute, University College London 2 , London, UK"},{"name":"Department of Medical Physics and Biomedical Engineering, University College London 3 , London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3183-7463","authenticated-orcid":false,"given":"Vanessa","family":"Diaz-Zuccarini","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University College London 1 , London, UK"},{"name":"UCL Hawkes Institute, University College London 2 , London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6287-1106","authenticated-orcid":false,"given":"Stavroula","family":"Balabani","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, University College London 1 , London, UK"},{"name":"UCL Hawkes Institute, University College London 2 , London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"175","published-online":{"date-parts":[[2026,10,14]]},"reference":[{"key":"2026102010220769100_RSIF20260109C1","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/nrcardio.2016.179","article-title":"Peripheral artery disease: epidemiology and global perspectives","volume":"14","author":"Fowkes","year":"2017","journal-title":"Nat. Rev. Cardiol."},{"key":"2026102010220769100_RSIF20260109C2","doi-asserted-by":"crossref","first-page":"afae114","DOI":"10.1093\/ageing\/afae114","article-title":"New horizons in peripheral artery disease","volume":"53","author":"Houghton","year":"2024","journal-title":"Age Ageing"},{"key":"2026102010220769100_RSIF20260109C3","doi-asserted-by":"crossref","first-page":"101082","DOI":"10.1016\/j.cpcardiol.2021.101082","article-title":"Peripheral artery disease: a comprehensive updated review","volume":"47","author":"Shamaki","year":"2022","journal-title":"Curr. Probl. Cardiol."},{"key":"2026102010220769100_RSIF20260109C4","doi-asserted-by":"crossref","first-page":"116288","DOI":"10.1016\/j.cma.2023.116288","article-title":"Design of innovative self-expandable femoral stents using inverse homogenization topology optimization","volume":"416","author":"Carbonaro","year":"2023","journal-title":"Comput. Meth. Appl. Mech. Eng."},{"key":"2026102010220769100_RSIF20260109C5","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.medengphy.2019.10.005","article-title":"Computing patient-specific hemodynamics in stented femoral artery models obtained from computed tomography using a validated 3D reconstruction method","volume":"75","author":"Colombo","year":"2020","journal-title":"Med. Eng. Phys."},{"key":"2026102010220769100_RSIF20260109C6","doi-asserted-by":"crossref","first-page":"105248","DOI":"10.1016\/j.compbiomed.2022.105248","article-title":"Superficial femoral artery stenting: impact of stent design and overlapping on the local hemodynamics","volume":"143","author":"Colombo","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"2026102010220769100_RSIF20260109C7","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.1038\/s41598-020-80681-8","article-title":"Baseline local hemodynamics as predictor of lumen remodeling at 1-year follow-up in stented superficial femoral arteries","volume":"11","author":"Colombo","year":"2021","journal-title":"Sci. Rep."},{"key":"2026102010220769100_RSIF20260109C8","doi-asserted-by":"crossref","first-page":"2203","DOI":"10.1007\/s10439-024-03520-1","article-title":"Impact of tissue damage and hemodynamics on restenosis following percutaneous transluminal angioplasty: a patient-specific multiscale model","volume":"52","author":"Corti","year":"2024","journal-title":"Ann. Biomed. Eng."},{"key":"2026102010220769100_RSIF20260109C9","doi-asserted-by":"crossref","first-page":"1883","DOI":"10.1007\/s10237-019-01183-9","article-title":"Prediction of restenosis based on hemodynamical markers in revascularized femoro-popliteal arteries during leg flexion","volume":"18","author":"G\u00f6kg\u00f6l","year":"2019","journal-title":"Biomech. Model. Mechanobiol."},{"key":"2026102010220769100_RSIF20260109C10","doi-asserted-by":"crossref","first-page":"108214","DOI":"10.1016\/j.cmpb.2024.108214","article-title":"Modelling lower-limb peripheral arterial disease using clinically available datasets: impact of inflow boundary conditions on hemodynamic indices for restenosis prediction","volume":"251","author":"Ninno","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"2026102010220769100_RSIF20260109C11","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1016\/j.jvscit.2019.09.009","article-title":"Multiscale, patient-specific computational fluid dynamics models predict formation of neointimal hyperplasia in saphenous vein grafts","volume":"6","author":"Donadoni","year":"2020","journal-title":"J. Vasc. Surg. Cases Innov. Tech."},{"key":"2026102010220769100_RSIF20260109C12","first-page":"100128","article-title":"A systematic review of clinical and biomechanical engineering perspectives on the prediction of restenosis in coronary and peripheral arteries","volume":"4","author":"Ninno","year":"2023","journal-title":"J. Vasc. Surg."},{"key":"2026102010220769100_RSIF20260109C13","doi-asserted-by":"crossref","first-page":"20170632","DOI":"10.1098\/rsif.2017.0632","article-title":"Computational tools for clinical support: a multi-scale compliant model for haemodynamic simulations in an aortic dissection based on multi-modal imaging data","volume":"14","author":"Bonfanti","year":"2017","journal-title":"J. R. Soc. Interface"},{"key":"2026102010220769100_RSIF20260109C14","doi-asserted-by":"crossref","first-page":"2950","DOI":"10.1007\/s10439-020-02603-z","article-title":"A combined in vivo, in vitro, in silico approach for patient-specific haemodynamic studies of aortic dissection","volume":"48","author":"Bonfanti","year":"2020","journal-title":"Ann. Biomed. Eng."},{"key":"2026102010220769100_RSIF20260109C15","doi-asserted-by":"crossref","first-page":"110793","DOI":"10.1016\/j.jbiomech.2021.110793","article-title":"A novel MRI-based data fusion methodology for efficient, personalised, compliant simulations of aortic haemodynamics","volume":"129","author":"Stokes","year":"2021","journal-title":"J. Biomech."},{"key":"2026102010220769100_RSIF20260109C16","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1007\/s10439-023-03175-4","article-title":"The influence of minor aortic branches in patient-specific flow simulations of type-B aortic dissection","volume":"51","author":"Stokes","year":"2023","journal-title":"Ann. Biomed. Eng."},{"key":"2026102010220769100_RSIF20260109C17","doi-asserted-by":"crossref","first-page":"377","DOI":"10.31083\/j.rcm2311377","article-title":"Current and future applications of computational fluid dynamics in coronary artery disease","volume":"23","author":"Candreva","year":"2022","journal-title":"Rev. Cardiovasc. Med."},{"key":"2026102010220769100_RSIF20260109C18","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1161\/ATVBAHA.123.320337","article-title":"Predicting lipid-rich plaque progression in coronary arteries using multimodal imaging and wall shear stress signatures","volume":"44","author":"De Nisco","year":"2024","journal-title":"Arterioscler. Thromb. Vasc. Biol."},{"key":"2026102010220769100_RSIF20260109C19","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1093\/cvr\/cvz212","article-title":"Multidirectional wall shear stress promotes advanced coronary plaque development: comparing five shear stress metrics","volume":"116","author":"Hoogendoorn","year":"2020","journal-title":"Cardiovasc. Res."},{"key":"2026102010220769100_RSIF20260109C20","doi-asserted-by":"crossref","first-page":"2201","DOI":"10.1038\/s41598-024-52398-5","article-title":"Methodology of generation of CFD meshes and 4D shape reconstruction of coronary arteries from patient-specific dynamic CT","volume":"14","author":"Psiuk-Maksymowicz","year":"2024","journal-title":"Sci. Rep."},{"key":"2026102010220769100_RSIF20260109C21","doi-asserted-by":"crossref","first-page":"20230281","DOI":"10.1098\/rsif.2023.0281","article-title":"Aneurysmal growth in type-B aortic dissection: assessing the impact of patient-specific inlet conditions on key haemodynamic indices","volume":"20","author":"Stokes","year":"2023","journal-title":"J. R. Soc. Interface"},{"key":"2026102010220769100_RSIF20260109C22","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.medengphy.2018.04.014","article-title":"A simplified method to account for wall motion in patient-specific blood flow simulations of aortic dissection: comparison with fluid-structure interaction","volume":"58","author":"Bonfanti","year":"2018","journal-title":"Med. Eng. Phys."},{"key":"2026102010220769100_RSIF20260109C23","doi-asserted-by":"crossref","first-page":"1360330","DOI":"10.3389\/fbioe.2024.1360330","article-title":"Rapid prediction of wall shear stress in stenosed coronary arteries based on deep learning","volume":"12","author":"Alamir","year":"2024","journal-title":"Front. Bioeng. Biotechnol."},{"key":"2026102010220769100_RSIF20260109C24","doi-asserted-by":"crossref","first-page":"110074","DOI":"10.1016\/j.compbiomed.2025.110074","article-title":"Role of physics-informed constraints in real-time estimation of 3D vascular fluid dynamics using multi-case neural network","volume":"190","author":"Chan","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"2026102010220769100_RSIF20260109C25","doi-asserted-by":"crossref","first-page":"116155","DOI":"10.1016\/j.cma.2023.116155","article-title":"FastSVD-ML\u2013ROM: a reduced-order modeling framework based on machine learning for real-time applications","volume":"414","author":"Drakoulas","year":"2023","journal-title":"Comput. Meth. Appl. Mech. Eng."},{"key":"2026102010220769100_RSIF20260109C26","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1063\/5.0101128","article-title":"Deep learning-based surrogate model for three-dimensional patient-specific computational fluid dynamics","volume":"34","author":"Du","year":"2022","journal-title":"Phys. Fluids"},{"key":"2026102010220769100_RSIF20260109C27","doi-asserted-by":"crossref","first-page":"109544","DOI":"10.1016\/j.jbiomech.2019.109544","article-title":"A feasibility study of deep learning for predicting hemodynamics of human thoracic aorta","volume":"99","author":"Liang","year":"2019","journal-title":"J. Biomech."},{"key":"2026102010220769100_RSIF20260109C28","doi-asserted-by":"crossref","first-page":"e3848","DOI":"10.1002\/cnm.3848","article-title":"Reduced order modelling of intracranial aneurysm flow using proper orthogonal decomposition and neural networks","volume":"40","author":"MacRaild","year":"2024","journal-title":"Int. J. Numer. Methods Biomed. Eng."},{"key":"2026102010220769100_RSIF20260109C29","doi-asserted-by":"crossref","first-page":"e1011055","DOI":"10.1371\/journal.pcbi.1011055","article-title":"Shape-driven deep neural networks for fast acquisition of aortic 3D pressure and velocity flow fields","volume":"19","author":"Pajaziti","year":"2023","journal-title":"PLoS Comput. Biol."},{"key":"2026102010220769100_RSIF20260109C30","doi-asserted-by":"crossref","first-page":"11577","DOI":"10.1038\/s41598-024-62117-9","article-title":"Strategies for multi-case physics-informed neural networks for tube flows: a study using 2D flow scenarios","volume":"14","author":"Wong","year":"2024","journal-title":"Sci. Rep."},{"key":"2026102010220769100_RSIF20260109C31","doi-asserted-by":"crossref","first-page":"e1012231","DOI":"10.1371\/journal.pcbi.1012231","article-title":"Image2Flow: a proof-of-concept hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D cardiac MRI data","volume":"20","author":"Yao","year":"2024","journal-title":"PLoS Comput. Biol."},{"key":"2026102010220769100_RSIF20260109C32","doi-asserted-by":"crossref","first-page":"20240774","DOI":"10.1098\/rsif.2024.0774","article-title":"A predictive surrogate model of blood haemodynamics for patient-specific carotid artery stenosis","volume":"22","author":"Barzegar Gerdroodbary","year":"2025","journal-title":"J. R. Soc. Interface"},{"key":"2026102010220769100_RSIF20260109C33","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/s10915-022-02082-5","article-title":"Data-driven reduced order modelling for patient-specific hemodynamics of coronary artery bypass grafts with physical and geometrical parameters","volume":"94","author":"Siena","year":"2023","journal-title":"J. Sci. Comput."},{"key":"2026102010220769100_RSIF20260109C34","doi-asserted-by":"crossref","first-page":"e0325644","DOI":"10.1371\/journal.pone.0325644","article-title":"ML-ROM wall shear stress prediction in patient-specific vascular pathologies under a limited clinical training data regime","volume":"20","author":"Chatpattanasiri","year":"2025","journal-title":"PLoS ONE"},{"key":"2026102010220769100_RSIF20260109C35","doi-asserted-by":"crossref","first-page":"111759","DOI":"10.1016\/j.jbiomech.2023.111759","article-title":"Towards reduced order models via robust proper orthogonal decomposition to capture personalised aortic haemodynamics","volume":"158","author":"Chatpattanasiri","year":"2023","journal-title":"J. Biomech."},{"key":"2026102010220769100_RSIF20260109C36","doi-asserted-by":"crossref","first-page":"e3858","DOI":"10.1002\/cnm.3858","article-title":"A comparison of machine learning methods for recovering noisy and missing 4D flow MRI data","volume":"40","author":"Csala","year":"2024","journal-title":"Int. J. Numer. Methods Biomed. Eng."},{"key":"2026102010220769100_RSIF20260109C37","doi-asserted-by":"crossref","first-page":"105729","DOI":"10.1016\/j.cmpb.2020.105729","article-title":"Super-resolution and denoising of 4D-flow MRI using physics-informed deep neural nets","volume":"197","author":"Fathi","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"2026102010220769100_RSIF20260109C38","doi-asserted-by":"crossref","first-page":"138","DOI":"10.3389\/fphy.2020.00138","article-title":"4DFlowNet: super-resolution 4D flow MRI using deep learning and computational fluid dynamics","volume":"8","author":"Ferdian","year":"2020","journal-title":"Front. Phys."},{"key":"2026102010220769100_RSIF20260109C39","doi-asserted-by":"crossref","first-page":"A40","DOI":"10.1017\/jfm.2022.503","article-title":"Joint reconstruction and segmentation of noisy velocity images as an inverse Navier\u2013Stokes problem","volume":"944","author":"Kontogiannis","year":"2022","journal-title":"J. Fluid Mech."},{"key":"2026102010220769100_RSIF20260109C40","volume-title":"Introduction to machine learning","author":"Alpaydin","year":"2020"},{"key":"2026102010220769100_RSIF20260109C41","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/JPROC.2023.3247480","article-title":"Model-based deep learning","volume":"111","author":"Shlezinger","year":"2020","journal-title":"Proc. IEEE"},{"key":"2026102010220769100_RSIF20260109C42","doi-asserted-by":"crossref","first-page":"20200802","DOI":"10.1098\/rsif.2020.0802","article-title":"Data-driven cardiovascular flow modelling: examples and opportunities","volume":"18","author":"Arzani","year":"2021","journal-title":"J. R. Soc. Interface"},{"key":"2026102010220769100_RSIF20260109C43","doi-asserted-by":"crossref","DOI":"10.1017\/9781009089517","volume-title":"Data-driven science and engineering: machine learning, dynamical systems, and control","author":"Brunton","year":"2022","edition":"2nd edn."},{"key":"2026102010220769100_RSIF20260109C44","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1007\/s11692-018-9464-9","article-title":"Dimensionality reduction techniques for visualizing morphometric data: comparing principal component analysis to nonlinear methods","volume":"46","author":"Du","year":"2018","journal-title":"Evol. Biol."},{"key":"2026102010220769100_RSIF20260109C45","doi-asserted-by":"crossref","first-page":"031901","DOI":"10.1063\/1.5083054","article-title":"Reduced-order modeling of left ventricular flow subject to aortic valve regurgitation","volume":"31","author":"Di Labbio","year":"2019","journal-title":"Phys. Fluids"},{"key":"2026102010220769100_RSIF20260109C46","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84882-955-8","volume-title":"Noninvasive peripheral arterial diagnosis","author":"AbuRahma","year":"2010"},{"key":"2026102010220769100_RSIF20260109C47","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s10439-008-9590-0","article-title":"Methods for quantifying three-dimensional deformation of arteries due to pulsatile and nonpulsatile forces: implications for the design of stents and stent grafts","volume":"37","author":"Choi","year":"2009","journal-title":"Ann. Biomed. Eng."},{"key":"2026102010220769100_RSIF20260109C48","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1161\/CIRCULATIONAHA.107.689141","article-title":"Nitinol stent implantation versus percutaneous transluminal angioplasty in superficial femoral artery lesions up to 10 cm in length: the femoral artery stenting trial (fast)","volume":"116","author":"Krankenberg","year":"2007","journal-title":"Circulation"},{"key":"2026102010220769100_RSIF20260109C49","first-page":"71","article-title":"Detailed cross-sectional study of 60 superficial femoral artery occlusions: morphological quantitative analysis can lead to a new classification","volume":"4","author":"Ohana","year":"2014","journal-title":"Cardiovasc. Diagn. Ther."},{"key":"2026102010220769100_RSIF20260109C50","doi-asserted-by":"crossref","first-page":"1867","DOI":"10.1007\/s10237-019-01182-w","article-title":"Reduced-order modeling of blood flow for noninvasive functional evaluation of coronary artery disease","volume":"18","author":"Buoso","year":"2019","journal-title":"Biomech. Model. Mechanobiol."},{"key":"2026102010220769100_RSIF20260109C51","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.3389\/fphys.2019.01329","article-title":"Blood rheology: key parameters, impact on blood flow, role in sickle cell disease and effects of exercise","volume":"10","author":"Nader","year":"2019","journal-title":"Front. Physiol."},{"key":"2026102010220769100_RSIF20260109C52","doi-asserted-by":"crossref","first-page":"1634","DOI":"10.3389\/fphys.2018.01634","article-title":"Acute tachycardia increases aortic distensibility, but reduces total arterial compliance up to a moderate heart rate","volume":"9","author":"Huo","year":"2018","journal-title":"Front. Physiol."},{"key":"2026102010220769100_RSIF20260109C53","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1007\/s13239-024-00723-4","article-title":"Literature survey for in-vivo Reynolds and Womersley numbers of various arteries and implications for compliant in-vitro modelling","volume":"15","author":"Williamson","year":"2024","journal-title":"Cardiovasc. Eng. Technol."},{"key":"2026102010220769100_RSIF20260109C54","doi-asserted-by":"crossref","first-page":"e0186300","DOI":"10.1371\/journal.pone.0186300","article-title":"Characteristics of pulsatile flows in curved stenosed channels","volume":"12","author":"Hong","year":"2017","journal-title":"PLoS ONE"},{"key":"2026102010220769100_RSIF20260109C55","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1007\/s10439-025-03737-8","article-title":"In silico, patient-specific assessment of local hemodynamic predictors and neointimal hyperplasia localisation in an arteriovenous graft","volume":"53","author":"Ninno","year":"2025","journal-title":"Ann. Biomed. Eng."},{"key":"2026102010220769100_RSIF20260109C56","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1146\/annurev.fl.25.010193.002543","article-title":"The proper orthogonal decomposition in the analysis of turbulent flows","volume":"25","author":"Berkooz","year":"1993","journal-title":"Annu. Rev. Fluid Mech."},{"key":"2026102010220769100_RSIF20260109C57","first-page":"333","article-title":"Addressing imbalance in multi-label classification using weighted cross entropy loss function","volume-title":"2020 27th National and 5th Int. Iranian Conf. on biomedical engineering (ICBME)","author":"Rezaei-Dastjerdehei","year":"2020"},{"key":"2026102010220769100_RSIF20260109C58","first-page":"2623","article-title":"Optuna: a next-generation hyperparameter optimization framework","volume-title":"Proc. of the 25th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining","author":"Akiba","year":"2019"},{"key":"2026102010220769100_RSIF20260109C59","first-page":"13686","article-title":"Imbalanced data problem in machine learning: a review","volume":"13","author":"Altalhan","year":"2025","journal-title":"IEEE"},{"key":"2026102010220769100_RSIF20260109C60","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1038\/s41592-023-01886-z","article-title":"Machine learning in rare disease","volume":"20","author":"Banerjee","year":"2023","journal-title":"Nat. Methods"},{"key":"2026102010220769100_RSIF20260109C61","first-page":"2980","article-title":"Focal loss for dense object detection","volume-title":"Proc. of the IEEE Int. Conf. on Computer Vision (ICCV)","author":"Lin","year":"2017"},{"key":"2026102010220769100_RSIF20260109C62","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1007\/978-3-030-75768-7_31","article-title":"Addressing the class imbalance problem in medical image segmentation via accelerated tversky loss function","volume-title":"Advances in knowledge discovery and data mining: 25th Pacific-Asia Conference, PAKDD 2021, Virtual Event, 11\u201314 May 2021, Proceedings, Part III","author":"Nasalwai","year":"2021"},{"key":"2026102010220769100_RSIF20260109C63","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1007\/978-3-319-67389-9_44","article-title":"Tversky loss function for image segmentation using 3D fully convolutional deep networks","volume-title":"Machine learning in medical imaging: 8th International Workshop, MLMI 2017, held in conjunction with MICCAI 2017, Quebec City, QC, Canada, 10 September 2017","author":"Salehi","year":"2017"},{"key":"2026102010220769100_RSIF20260109C64","doi-asserted-by":"crossref","first-page":"18814","DOI":"10.1109\/TNNLS.2023.3321753","article-title":"Merge loss calculation method for highly imbalanced data multiclass classification","volume":"35","author":"Du","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2026102010220769100_RSIF20260109C65","doi-asserted-by":"crossref","first-page":"751","DOI":"10.1007\/s13042-019-00982-x","article-title":"Combination of loss functions for deep text classification","volume":"11","author":"Hajiabadi","year":"2020","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"2026102010220769100_RSIF20260109C66","doi-asserted-by":"crossref","first-page":"e0177678","DOI":"10.1371\/journal.pone.0177678","article-title":"Optimal classifier for imbalanced data using Matthews correlation coefficient metric","volume":"12","author":"Boughorbel","year":"2017","journal-title":"PLoS ONE"},{"key":"2026102010220769100_RSIF20260109C67","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genomics"},{"key":"2026102010220769100_RSIF20260109C68","doi-asserted-by":"crossref","first-page":"8342104","DOI":"10.1155\/2023\/8342104","article-title":"Deep learning with graph convolutional networks: an overview and latest applications in computational intelligence","volume":"2023","author":"Bhatti","year":"2023","journal-title":"Int. J. Intell. Syst."},{"key":"2026102010220769100_RSIF20260109C69","doi-asserted-by":"crossref","first-page":"107676","DOI":"10.1016\/j.compbiomed.2023.107676","article-title":"Learning reduced-order models for cardiovascular simulations with graph neural networks","volume":"168","author":"Pegolotti","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"2026102010220769100_RSIF20260109C70","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1007\/s10462-024-10862-8","article-title":"A brief review of hypernetworks in deep learning","volume":"57","author":"Chauhan","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"2026102010220769100_RSIF20260109C71","first-page":"1","article-title":"Neural implicit flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal data","volume-title":"J. Mach. Learn Res.","author":"Pan","year":"2023"},{"key":"2026102010220769100_RSIF20260109C72","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.1007\/s10409-021-01148-1","article-title":"Physics-informed neural networks (PINNs) for fluid mechanics: a review","volume":"37","author":"Cai","year":"2021","journal-title":"Acta Mech. Sin."},{"key":"2026102010220769100_RSIF20260109C73","doi-asserted-by":"crossref","first-page":"109644","DOI":"10.1016\/j.compbiomed.2024.109644","article-title":"Physics-constrained coupled neural differential equations for one dimensional blood flow modeling","volume":"186","author":"Csala","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"2026102010220769100_RSIF20260109C74","doi-asserted-by":"crossref","first-page":"110666","DOI":"10.1016\/j.jcp.2021.110666","article-title":"Physics-informed machine learning for reduced-order modeling of nonlinear problems","volume":"446","author":"Chen","year":"2021","journal-title":"J. Comput. Phys."},{"key":"2026102010220769100_RSIF20260109C75","doi-asserted-by":"crossref","first-page":"115771","DOI":"10.1016\/j.cma.2022.115771","article-title":"Physics-data combined machine learning for parametric reduced-order modelling of nonlinear dynamical systems in small-data regimes","volume":"404","author":"Fu","year":"2023","journal-title":"Comput. Meth. Appl. Mech. Eng."},{"key":"2026102010220769100_RSIF20260109C76","article-title":"Workflow and datasets for a data-driven framework to identify restenosis-prone regions in femoral arteries from geometric and inflow waveform parameters","author":"Chatpattanasiri","year":"2026"},{"key":"2026102010220769100_RSIF20260109C77","article-title":"Supplementary material from: A data-driven framework to identify restenosis-prone regions in femoral arteries from geometric and inflow waveform parameters","author":"Chatpattanasiri","year":"2026"}],"container-title":["Journal of the Royal Society Interface"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/royalsocietypublishing.org\/rsif\/article-pdf\/doi\/10.1098\/rsif.2026.0109\/6170331\/rsif.2026.0109.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/royalsocietypublishing.org\/rsif\/article-pdf\/doi\/10.1098\/rsif.2026.0109\/6170331\/rsif.2026.0109.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T14:52:22Z","timestamp":1792507942000},"score":1,"resource":{"primary":{"URL":"https:\/\/royalsocietypublishing.org\/rsif\/article\/23\/243\/20260109\/483627\/A-data-driven-framework-to-identify-restenosis"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":77,"journal-issue":{"issue":"243","published-print":{"date-parts":[[2026,10,7]]}},"URL":"https:\/\/doi.org\/10.1098\/rsif.2026.0109","relation":{},"ISSN":["1742-5689","1742-5662"],"issn-type":[{"value":"1742-5689","type":"print"},{"value":"1742-5662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"20260109"}}