Advancing biomaterial research with artificial intelligence
Document Type
Article
Publication Date
3-1-2026
Abstract
Biomaterials play a crucial role in the healthcare sector, particularly in applications involving implantation into the human body, where preventing adverse effects is of paramount importance. Artificial intelligence (AI) has become an essential tool in biomaterial research to accelerate the development and innovations of biomaterials across different applications while addressing challenges in fabrication and characterization processes that were traditionally time-consuming, labor-intensive, and costly. By leveraging AI, researchers can enhance the performance, efficiency, and scalability of biomaterial development. This review provides a detailed examination of the applications of Machine Learning and Deep Learning across various biomaterial categories, including polymeric, metallic, ceramic, and composite biomaterials. It also explores fundamental AI methodologies, including supervised, unsupervised, semi-supervised and reinforcement learning, highlighting their roles in tackling forward and inverse design problems. Beyond the benefits, the review discusses key limitations of AI, such as model interpretability, data quality, and overfitting, along with emerging solutions like Explainable Artificial Intelligence, integrating methods such as Sharpley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) to address these challenges. Together, these insights underscore the potential and evolving landscape of AI in advancing biomaterial research.
Keywords
Artificial intelligence, Ceramic biomaterial, Composite biomaterial, Explainable artificial intelligence, Machine learning, Metallic biomaterial, Polymer biomaterial
Publication Title
Biomaterials Advances
ISSN
2772-9508
DOI
10.1016/j.bioadv.2025.214535
Recommended Citation
Ng, Jun Chen; Yeoh, Pauline Shan Qing; Muhamad, Farina; Zhao, Xiao Xu; Wu, Shui Lin; Wu, Xiang; and Lai, Khin Wee, "Advancing biomaterial research with artificial intelligence" (2026). Research Publications (2026 to 2030). 1107.
https://knova.um.edu.my/research_publications_2026_2030/1107
Volume
180
Publisher
Elsevier Ltd