Machine learning for forecasting the biomechanical behavior of orthopedic bone plates fabricated by fused deposition modeling

Abstract

Purpose Three-dimensional (3D) printing is highly dependent on printing process parameters for achieving high mechanical strength. It is a time-consuming and expensive operation to experiment with different printing settings. The current study aims to propose a regression-based machine learning model to predict the mechanical behavior of ulna bone plates. Design/methodology/approach The bone plates were formed using fused deposition modeling (FDM) technique, with printing attributes being varied. The machine learning models such as linear regression, AdaBoost regression, gradient boosting regression (GBR), random forest, decision trees and k-nearest neighbors were trained for predicting tensile strength and flexural strength. Model performance was assessed using root mean square error (RMSE), coefficient of determination (R2) and mean absolute error (MAE). Findings Traditional experimentation with various settings is both time-consuming and expensive, emphasizing the need for alternative approaches. Among the models tested, GBR model demonstrated the best performance in predicting both tensile and flexural strength and achieved the lowest RMSE, highest R2 and lowest MAE, which are 1.4778 ± 0.4336 MPa, 0.9213 ± 0.0589 and 1.2555 ± 0.3799 MPa, respectively, and 3.0337 ± 0.3725 MPa, 0.9269 ± 0.0293 and 2.3815 ± 0.2915 MPa, respectively. The findings open up opportunities for doctors and surgeons to use GBR as a reliable tool for fabricating patient-specific bone plates, without the need for extensive trial experiments. Research limitations/implications The current study is limited to the usage of a few models. Other machine learning-based models can be used for prediction-based study. Originality/value This study uses machine learning to predict the mechanical properties of FDM-based distal ulna bone plate, replacing traditional design of experiments methods with machine learning to streamline the production of orthopedic implants. It helps medical professionals, such as physicians and surgeons, make informed decisions when fabricating customized bone plates for their patients while reducing the need for time-consuming experimentation, thereby addressing a common limitation of 3D printing medical implants.

Design for additive manufacturing of topology-optimized structures based on deep learning and transfer learning

“…Machine learning (ML) has been extensively used in AM for different purposes. ML networks have been trained in designing for AM (material and topology design), AM process (process optimization, online monitoring) and AM production (manufacturing planning, quality control) (Wang et al , 2020; Xames et al , 2023; Sharma et al , 2024). Recently, many intelligent systems have been presented for TO (Li et al , 2019; Shen and M, 2019; Yu et al , 2019; Qian and Ye, 2021; Rade, 2021).…”