Page 5 - IJB-7-1

PERSPECTIVE ARTICLE

Application of Machine Learning in 3D Bioprinting:

Focus on Development of Big Data and Digital Twin

Jia An , Chee Kai Chua , Vladimir Mironov *
1
2
3
1 Singapore Centre for 3D Printing, School of Mechanical and Aerospace Engineering, Nanyang Technological University,
50 Nanyang Avenue, Singapore 639798
2 Engineering Product Development, Singapore University of Technology and Design, 8 Somapah Road, Singapore 487372
3 3D Bioprinting Solutions, 68/2 Kashirskoe Highway, Moscow, Russian Federation 115409

Abstract: The application of machine learning (ML) in bioprinting has attracted considerable attention recently. Many have
focused on the benefits and potential of ML, but a clear overview of how ML shapes the future of three-dimensional (3D)
bioprinting is still lacking. Here, it is proposed that two missing links, Big Data and Digital Twin, are the key to articulate
the vision of future 3D bioprinting. Creating training databases from Big Data curation and building digital twins of human
organs with cellular resolution and properties are the most important and urgent challenges. With these missing links, it is
envisioned that future 3D bioprinting will become more digital and in silico, and eventually strike a balance between virtual
and physical experiments toward the most efficient utilization of bioprinting resources. Furthermore, the virtual component of
bioprinting and biofabrication, namely, digital bioprinting, will become a new growth point for digital industry and information
technology in future.
Keywords: 3D bioprinting; Complexity; Machine learning; Big data; Digital twin

*Correspondence to: Vladimir Mironov, 3D Bioprinting Solutions, 68/2 Kashirskoe highway, Moscow, Russian Federation 115409;
vladimir.mironov54@gmail.com
Received: January 8, 2021; Accepted: January 18, 2021; Published Online: January 29, 2021

Citation: An J, Chua CK, Mironov V., 2021, Application of Machine Learning in 3D Bioprinting: Focus on Development of
Big Data and Digital Twin. Int J Bioprint, 7(1):342. http://doi.org/10.18063/ijb.v7i1.342

1. Introduction able to find a relationship between X and Y as a function
of Y(X). If the input has multiple variables ranging from
Recently, there is surge in scientific publications X to X and the output Y to Y , humans will be easily
0
n
0
regarding the application of machine learning (ML) to overwhelmed by the complexities. However, computer
n
bioprinting-relevant researches such as medical imaging algorithms can replace human to “inspect” the input and
and segmentation, optimization of bioinks or bioprinting output and “guess” an approximate function among them.
process as well as in vitro parametric studies, which are This approximate function generated by the algorithms is
well reviewed in Yu and Jiang , Ng et al. . Both recent called ML model. The more input and output data there are,
[1]
[2]
articles focused on the benefits and potential of ML but the more accurate the ML model becomes. This approach
missed a clear portrait of what future bioprinting looks is known as mapping or supervised learning. In contrast,
like. This perspective article is, therefore, written as in grouping or unsupervised learning, the output (Y) is not
an extension of previous reviews, focusing on a vision given, the computer algorithms must figure out the output
of future three-dimensional (3D) bioprinting enabled on its own, such as a pattern, a cluster, or a relationship
by ML. in the input data (X , X ,… X ). Therefore, this approach
n
1
0
ML is a collection of computational methods of is best for uncovering hidden patterns or relationships
discovering approximate mathematical functions of the in data. Another approach in ML is reinforcement
real world based on historical data (Figure 1). Given a learning, in which both input (X , X … X ) and output
1
0
n
set of input (X) and output (Y) data, humans are usually (Y , Y … Y ) are known, the algorithms (or agent) are
0
1
n
© 2021 An, et al. This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License
(http://creativecommons.org/licenses/by-nc/4.0/), permitting all non-commercial use, distribution, and reproduction in any medium, provided the original
work is properly cited.
1