EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Machine learning-driven prediction of gel fraction in conductive gelatin methacryloyl hydrogels

Xi Huang, Ye Xuan Wong, Guo Liang Goh, Xinchao Gao, Jia Min Lee, Wai Yee Yeong

International Journal of AI for Materials and Design · 2024

DOI: 10.36922/ijamd.3807 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of AI for Materials and Design, 2024. Verfasst von Xi Huang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gelatin methacryloyl (GelMA) hydrogels, combined with conductive fillers like Poly(3,4-ethylenedioxythiophene) polystyrene sulfonate (PEDOT:SPSS), present significant promise for tissue regeneration due to their biocompatibility, biodegradability, and electrical conductivity. However, optimizing the curing process of the hydrogel is challenging due to a lack of an existing model for gel fraction prediction. This complexity is further heightened when additional variables such as bioink formulation and crosslinking parameters are considered. This study leverages machine learning (ML) to predict the gel fraction of GelMA-PEDOT:SPSS hydrogel based on the combination of three types of features: Bioink formulation, crosslinking parameters, and absorption coefficient. The two key objectives of this study are to develop an ML model to predict gel fraction from bioink formulation and crosslinking parameters such as ultraviolet (UV) power intensity and UV irradiation duration, and to create an ML model to predict gel fraction through the absorption coefficient instead of crosslinking parameter. In the first ML model, support vector regression achieved the highest accuracy with a mean absolute percentage error (MAPE) of 3.13% and an R² of 0.79. This model allows the user to select optimum bioink formulation and crosslinking parameters to achieve the required gel fraction with minimal experiment. For the second ML model that utilizes a combination of absorption coefficient and bioink formulation, deep neural network models achieved a MAPE of 6.31% and an R² of 0.54. The absorption coefficient model shows promise for a non-destructive, real-time assessment of gel fraction, enabling more precise control over the hydrogel properties during the curing process. These results demonstrate ML’s capability to efficiently optimize hydrogel formulations, significantly cut down experimental efforts, and improve precision in 3D bioprinting and other hydrogel applications, thereby advancing the field of tissue regeneration.

Zitieren

APA

Huang, X., Wong, Y. X., Goh, G. L., Gao, X., Lee, J. M., & Yeong, W. Y. (2024). Machine learning-driven prediction of gel fraction in conductive gelatin methacryloyl hydrogels. International Journal of AI for Materials and Design. https://doi.org/10.36922/ijamd.3807

Vancouver

Huang X, Wong YX, Goh GL, Gao X, Lee JM, Yeong WY. Machine learning-driven prediction of gel fraction in conductive gelatin methacryloyl hydrogels. International Journal of AI for Materials and Design. 2024. doi:10.36922/ijamd.3807

BibTeX
@article{Huang2024,
  author = {Huang, Xi and Wong, Ye Xuan and Goh, Guo Liang and Gao, Xinchao and Lee, Jia Min and Yeong, Wai Yee},
  title = {Machine learning-driven prediction of gel fraction in conductive gelatin methacryloyl hydrogels},
  journal = {International Journal of AI for Materials and Design},
  year = {2024},
  doi = {10.36922/ijamd.3807}
}
Kostenlos starten →