A Review for Machine Learning Applications in Characterizing Biomaterials and Biological Materials Properties

Abstract

Characterizing specific mechanical properties for biological materials and biomaterials remains an exciting topic within several research fields. The functionality of biological materials and biomaterials relies on their mechanical properties, such as elastic and shear modulus. While several sophisticated experimental techniques can perform in vivo and in vitro to characterize the material properties, the measurement exhibits a broad uncertainty due to the limitations in diagnostics and experimental randomness. Alternatively, Machine learning approaches evolve as an efficient and striking tool to process a massive amount of complex data sets simultaneously and discover the hidden correlation between the materials structure and dynamic responses. This work briefly reviews the advanced applications of machine learning algorithms in studies of the dynamic behavior of biological materials and the development of biomaterials. It is evident that machine learning approaches can significantly impact the clinical development in biomedical engineering and healthcare.