Using artificial neural networks to predict impingement and dislocation in total hip arthroplasty

Abstract Dislocation after total hip arthroplasty (THA) remains a major issue and an important post-surgical complication. Impingement and subsequent dislocation are influenced by the design (head size) and position (anteversion and abduction angles) of the acetabulum and different movements of the patient, with external extension and internal flexion the most critical movements. The aim of this study is to develop a computational tool based on a three-dimensional (3D) parametric finite element (FE) model and an artificial neural network (ANN) to assist clinicians in identifying the optimal prosthesis design and position of the acetabular cup to reduce the probability of impingement and dislocation. A 3D parametric model of a THA was used. The model parameters were the femoral head size and the acetabulum abduction and anteversion angles. Simulations run with this parametric model were used to train an ANN, which predicts the range of movement (ROM) before impingement and dislocation. This study recreates different configurations and obtains absolute errors lower than 5.5° between the ROM obtained from the FE simulations and the ANN predictions. The ROM is also predicted for patients who had already suffered dislocation after THA, and the computational predictions confirm the patient’s dislocations. Summarising, the combination of a 3D parametric FE model of a THA and an ANN is a useful computational tool to predict the ROM allowed for different designs of prosthesis heads.