An explainable machine learning-based probabilistic framework for the design of scaffolds in bone tissue engineering.
Saved in:
| Title: | An explainable machine learning-based probabilistic framework for the design of scaffolds in bone tissue engineering. |
|---|---|
| Authors: | Drakoulas, George1 (AUTHOR) g.drakoulas@upnet.gr, Gortsas, Theodore1,2 (AUTHOR) gortsas@upatras.gr, Polyzos, Efstratios3 (AUTHOR), Tsinopoulos, Stephanos2 (AUTHOR), Pyl, Lincy3 (AUTHOR), Polyzos, Demosthenes1 (AUTHOR) |
| Source: | Biomechanics & Modeling in Mechanobiology. Jun2024, Vol. 23 Issue 3, p987-1012. 26p. |
| Subjects: | Tissue scaffolds, Tissue engineering, Reduced-order models, Extracellular fluid, Deformation of surfaces, Polylactic acid, Bioactive glasses |
| Abstract: | Recently, 3D-printed biodegradable scaffolds have shown great potential for bone repair in critical-size fractures. The differentiation of the cells on a scaffold is impacted among other factors by the surface deformation of the scaffold due to mechanical loading and the wall shear stresses imposed by the interstitial fluid flow. These factors are in turn significantly affected by the material properties, the geometry of the scaffold, as well as the loading and flow conditions. In this work, a numerical framework is proposed to study the influence of these factors on the expected osteochondral cell differentiation. The considered scaffold is rectangular with a 0/90 lay-down pattern and a four-layered strut made of polylactic acid with a 5% steel particle content. The distribution of the different types of cells on the scaffold surface is estimated through a scalar stimulus, calculated by using a mechanobioregulatory model. To reduce the simulation time for the computation of the stimulus, a probabilistic machine learning (ML)-based reduced-order model (ROM) is proposed. Then, a sensitivity analysis is performed using the Shapley additive explanations to examine the contribution of the various parameters to the framework stimulus predictions. In a final step, a multiobjective optimization procedure is implemented using genetic algorithms and the ROM, aiming to identify the material parameters and loading conditions that maximize the percentage of surface area populated by bone cells while minimizing the area corresponding to the other types of cells and the resorption condition. The results of the performed analysis highlight the potential of using ROMs for the scaffold design, by dramatically reducing the simulation time while enabling the efficient implementation of sensitivity analysis and optimization procedures. [ABSTRACT FROM AUTHOR] |
| Copyright of Biomechanics & Modeling in Mechanobiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 178048238 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: An explainable machine learning-based probabilistic framework for the design of scaffolds in bone tissue engineering. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Drakoulas%2C+George%22">Drakoulas, George</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> g.drakoulas@upnet.gr</i><br /><searchLink fieldCode="AR" term="%22Gortsas%2C+Theodore%22">Gortsas, Theodore</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> gortsas@upatras.gr</i><br /><searchLink fieldCode="AR" term="%22Polyzos%2C+Efstratios%22">Polyzos, Efstratios</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tsinopoulos%2C+Stephanos%22">Tsinopoulos, Stephanos</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Pyl%2C+Lincy%22">Pyl, Lincy</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Polyzos%2C+Demosthenes%22">Polyzos, Demosthenes</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Biomechanics+%26+Modeling+in+Mechanobiology%22">Biomechanics & Modeling in Mechanobiology</searchLink>. Jun2024, Vol. 23 Issue 3, p987-1012. 26p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Tissue+scaffolds%22">Tissue scaffolds</searchLink><br /><searchLink fieldCode="DE" term="%22Tissue+engineering%22">Tissue engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Reduced-order+models%22">Reduced-order models</searchLink><br /><searchLink fieldCode="DE" term="%22Extracellular+fluid%22">Extracellular fluid</searchLink><br /><searchLink fieldCode="DE" term="%22Deformation+of+surfaces%22">Deformation of surfaces</searchLink><br /><searchLink fieldCode="DE" term="%22Polylactic+acid%22">Polylactic acid</searchLink><br /><searchLink fieldCode="DE" term="%22Bioactive+glasses%22">Bioactive glasses</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Recently, 3D-printed biodegradable scaffolds have shown great potential for bone repair in critical-size fractures. The differentiation of the cells on a scaffold is impacted among other factors by the surface deformation of the scaffold due to mechanical loading and the wall shear stresses imposed by the interstitial fluid flow. These factors are in turn significantly affected by the material properties, the geometry of the scaffold, as well as the loading and flow conditions. In this work, a numerical framework is proposed to study the influence of these factors on the expected osteochondral cell differentiation. The considered scaffold is rectangular with a 0/90 lay-down pattern and a four-layered strut made of polylactic acid with a 5% steel particle content. The distribution of the different types of cells on the scaffold surface is estimated through a scalar stimulus, calculated by using a mechanobioregulatory model. To reduce the simulation time for the computation of the stimulus, a probabilistic machine learning (ML)-based reduced-order model (ROM) is proposed. Then, a sensitivity analysis is performed using the Shapley additive explanations to examine the contribution of the various parameters to the framework stimulus predictions. In a final step, a multiobjective optimization procedure is implemented using genetic algorithms and the ROM, aiming to identify the material parameters and loading conditions that maximize the percentage of surface area populated by bone cells while minimizing the area corresponding to the other types of cells and the resorption condition. The results of the performed analysis highlight the potential of using ROMs for the scaffold design, by dramatically reducing the simulation time while enabling the efficient implementation of sensitivity analysis and optimization procedures. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Biomechanics & Modeling in Mechanobiology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=178048238 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s10237-024-01817-7 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 26 StartPage: 987 Subjects: – SubjectFull: Tissue scaffolds Type: general – SubjectFull: Tissue engineering Type: general – SubjectFull: Reduced-order models Type: general – SubjectFull: Extracellular fluid Type: general – SubjectFull: Deformation of surfaces Type: general – SubjectFull: Polylactic acid Type: general – SubjectFull: Bioactive glasses Type: general Titles: – TitleFull: An explainable machine learning-based probabilistic framework for the design of scaffolds in bone tissue engineering. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Drakoulas, George – PersonEntity: Name: NameFull: Gortsas, Theodore – PersonEntity: Name: NameFull: Polyzos, Efstratios – PersonEntity: Name: NameFull: Tsinopoulos, Stephanos – PersonEntity: Name: NameFull: Pyl, Lincy – PersonEntity: Name: NameFull: Polyzos, Demosthenes IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 16177959 Numbering: – Type: volume Value: 23 – Type: issue Value: 3 Titles: – TitleFull: Biomechanics & Modeling in Mechanobiology Type: main |
| ResultId | 1 |
