Towards the ideal vascular implant - Use of machine learning and statistical approaches to optimise manufacturing parameters

Aug 5, 2026

Upload by Jiven

Electrospinning enables fabrication of biomimetic nano-/microfibre scaffolds that emulate the extracellular matrix of vascular tissue, with morphology and mechanics controlled through manufacturing parameters. The study develops machine-learning and statistical models to optimise a PVA-based vascular implant setup. Fibre morphology and mechanical performance are characterised using scanning electron microscopy and mechanical testing to build predictive morphological and mechanical models. The optimised parameters yield scaffolds that closely replicate vascular tissue properties and demonstrate strong model performance.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Methods

Results

Discussion

Roldan Ciudad, Elisa ORCID logoORCID: [https://orcid.org/0000-0002-7793-](https://orcid.org/0000-0002-7793-)[ ](https://orcid.org/0000-0002-7793-)7542, Reeves, Neil ORCID logoORCID: [https://orcid.org/0000-0001-9213-](https://orcid.org/0000-0001-9213-)[ ](https://orcid.org/0000-0001-9213-)4580, Cooper, Glen and Andrews, Kirstie (2023) Towards the ideal vascular implant: Use of machine learning and statistical approaches to optimise manufacturing parameters. Frontiers in Physics, 11 . p. 1112218. ISSN 2296-424X Downloaded from: [https://e-space.mmu.ac.uk/631357/](https://e-space.mmu.ac.uk/631357/) Version: Published Version Publisher: Frontiers Media S.A. DOI: [https://doi.org/10.3389/fphy.2023.1112218](https://doi.org/10.3389/fphy.2023.1112218) [Usage rights:](Usage rights: Creative Commons: Attribution 4.0)[ Creative Commons: Attribution 4.0](Usage rights: Creative Commons: Attribution 4.0)[ ](Usage rights: Creative Commons: Attribution 4.0)Please cite the published version [https://e-space.mmu.ac.uk](https://e-space.mmu.ac.uk) TYPE Original Research PUBLISHED 07 February 2023 DOI 10.3389/fphy.2023.1112218 OPEN ACCESS EDITED BY Aike Qiao, Beijing University of Technology, China REVIEWED BY Gaoyang Li, Tohoku University, Japan Tinghui Zheng, Sichuan University, China *CORRESPONDENCE Elisa Roldán, [elisa.roldan-ciudad@mmu.ac.uk](elisa.roldan-ciudad@mmu.ac.uk) SPECIALTY SECTION This article was submitted to Biophysics, a section of the journal Frontiers in Physics RECEIVED 30 November 2022 ACCEPTED 18 January 2023 PUBLISHED 07 February 2023 CITATION Roldán E, Reeves ND, Cooper G and Andrews K (2023), Towards the ideal vascular implant: Use of machine learning and statistical approaches to optimise manufacturing parameters. Front. Phys. 11:1112218 . doi: 10.3389/fphy.2023.1112218 COPYRIGHT © 2023 Roldán, Reeves, Cooper and Andrews. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Towards the ideal vascular implant: Use of machine learning and statistical approaches to optimise manufacturing parameters Elisa Roldán 1*, Neil D. Reeves 2, Glen Cooper 3 and Kirstie Andrews 1 1 Department of Engineering, Faculty of Science and Engineering, Manchester Metropolitan University, Manchester, United Kingdom, 2Research Centre for Musculoskeletal Science and Sports Medicine, Department of Life Sciences, Faculty of Science and Engineering, Manchester Metropolitan University, Manchester, United Kingdom, 3School of Engineering, University of Manchester, Manchester, United Kingdom Introduction: Electrospinning is a manufacturing technique that creates a net of nano and microﬁbres able to mimic the natural extracellular matrix (ECM) of biological tissue. Electrospun scaffolds' morphology and mechanical behaviour can be tailored by modifying the environmental, solution and process parameters. This study aims to produce biomimetic vascular implants optimising the manufacturing set up through two machine learning techniques and statistical approaches. Methods: Polyvinyl alcohol (PVA) based scaffolds were produced by modifying the concentration of the polymer, ﬂow rate, voltage, type of collector, diameter of the needle, distance between needle and collector and revolutions of the mandrel. The scaffolds were morphologically and mechanically characterised using scanning electron microscopy and mechanical testing respectively to inform the morphological model (simultaneously predicting diameter of the ﬁbres and interﬁbre separation) and mechanical model (predicting strain at rupture and u

FAQs

What manufacturing method and materials are used to create the vascular implant scaffolds?

The study uses electrospinning to fabricate polyvinyl alcohol (PVA)-based scaffolds. Manufacturing inputs include polymer concentration, flow rate, voltage, collector type, needle diameter, needle-to-collector distance, and mandrel rotation.

How are the scaffolds evaluated to guide model optimisation?

Scaffolds are characterised morphologically and mechanically using scanning electron microscopy and mechanical testing. These measurements feed a morphological model and a mechanical model to predict fibre diameter, interfibre separation, strain at rupture, and ultimate tensile strength.

Which modelling approaches were compared, and what optimisation outcome was achieved?

The work compares CHAID decision-tree models, two-output artificial neural networks (ANN), and multivariate variance/covariance models (MANOVA/MANCOVA), alongside multi-linear regression (MLR). The optimised setup includes 12% PVA, 1 ml/h flow rate, 20 kV, 8 cm needle distance, 18 G needle, 15 cm mandrel rotation, and 2000 rpm, producing scaffolds that match key vascular tissue mechanical and structural properties.

Aug 5, 2026

Upload by Jiven