Computational evaluation of different numerical tools for the prediction of proximal femur loads from bone morphology

• We ideally estimate patient-specific loads from bone geometry and density measurement.
• We combine FE, bone remodeling models, and machine learning techniques.
• Linear regression and ANN computed a good load prediction with error less than 2%.
• The support vector machine technique predicts higher relative errors.
• ANN with multiple outputs obtained a high accuracy in the prediction of a known bone density.

Patient-specific modeling is becoming increasingly important. One of the most challenging difficulties in creating patient-specific models is the determination of the specific load that the bone is really supporting. Real information relating to specific patients, such as bone geometry and bone density distribution, can be used to determine these loads. The main goal of this study is to theoretically estimate patient-specific loads from bone geometry and density measurements, comparing different mathematical techniques: linear regression, artificial neural networks with individual or multiple outputs and support vector machines. This methodology has been applied to 2D/3D finite element models of a proximal femur with different results. Linear regression and artificial neural networks demonstrated a good load prediction with relative error less than 2%. However, the support vector machine technique predicted higher relative errors. Using artificial neural networks with multiple outputs we obtained a high degree of accuracy in the prediction of the load conditions that produce a known bone density distribution. Therefore, it is shown that the proposed method is capable of predicting the loading that induces a specific bone density distribution.