Machine Learning-Driven Optimization of 3D Printing Parameters for PLA Bone Scaffolds with Enhanced Mechanical Properties

Bone scaffolds have revolutionized orthopedic tissue regeneration, providing vital physical support during bone regrowth phases and subsequently being absorbed into the body. The mechanical properties of these scaffolds, such as Young's modulus, closely mimicking that of natural bone tissue, can significantly enhance osteogenesis and stimulate bone repair. In the realm of 3D printing, ensuring the mechanical fidelity of biodegradable Polylactic Acid (PLA) scaffolds is crucial. However, achieving this requires a thorough understanding of how manufacturing parameters influence scaffold performance. In this study, we employed a range of machine learning techniques to predict the mechanical attributes of PLA bone scaffolds. These techniques included Linear Regression, Polynomial Regression, Decision Tree, Random Forest, Support Vector Regression (SVR), and Gradient Boosting. Each method was selected to analyze the impact of three pivotal printing parameters: nozzle temperature, printing speed, and cooling rate, on the scaffold's mechanical properties. The study sought to establish connections between printing conditions and scaffold mechanical properties, the findings underscore the complex nature of these relationships, highlighting the potential of machine learning to contribute to a data-informed approach in scaffold production.