Harnessing machine learning algorithms for the prediction and optimization of various properties of polylactic acid in biomedical use: a comprehensive review.
Journal:
Biomedical materials (Bristol, England)
PMID:
39787713
Abstract
Machine learning (ML) has emerged as a transformative tool in various industries, driving advancements in key tasks like classification, regression, and clustering. In the field of chemical engineering, particularly in the creation of biomedical devices, personalization is essential for ensuring successful patient recovery and rehabilitation. Polylactic acid (PLA) is a material with promising potential for applications like tissue engineering, orthopedic implants, drug delivery systems, and cardiovascular stents due to its biocompatibility and biodegradability. Additive manufacturing (AM) allows for adjusting print parameters to optimize the properties of PLA components for different applications. Although past research has explored the integration of ML and AM, there remains a gap in comprehensive analyses focusing on the impact of ML on PLA-based biomedical devices. This review examines the most recent developments in ML applications within AM, highlighting its ability to revolutionize the utilization of PLA in biomedical engineering by enhancing material properties and optimizing manufacturing processes. Moreover, this review is in line with the journal's emphasis on bio-based polymers, polymer functionalization, and their biomedical uses, enriching the understanding of polymer chemistry and materials science.