A data-driven ensemble machine learning approach for predicting the mechanical strength of 3D printed orthopaedic bone screws

Abstract

The mechanical strength of three-dimensional (3D) printed orthopaedic bone screws plays a major role in load-bearing bone fractures and deformities. Orthopaedic screws need to have enough mechanical strength to support and rehabilitate fracture sites under loads. Several process parameters are used in 3D printing technology for part fabrication; monitoring the mechanical strength of fabricated parts is a difficult and tedious task. The prediction of mechanical strength by a data-driven machine learning (ML) approach can be the solution. The present work leverages ensemble ML algorithms for predicting the mechanical strength of 3D-printed orthopaedic screws. Fused deposition modelling-based technology is utilised for orthopaedic cortical screw fabrication. Different process parameters were varied at different levels for the fabrication of orthopaedic screws. Ensemble ML techniques such as XGBoost, AdaBoost and GradientBoost are employed. The robustness and performance of predictive models were compared at different error metrics to offer an adequate predictive ML model. The XGBoost ensemble model was observed to be the most accurate with the least error metrics. Honeycomb-patterned with 100% infill percentage, layer height of 0.06 mm, and wall thickness of 1 mm may be selected for the maximum strength of a 3D-printed cortical screw. Moreover, the ensemble ML model's predictive performance and adequacy were higher than the base learning models.