Prediction of load in the equine third metacarpal forelimb through neural network prediction algorithm

Equine third metacarpal (MC3) bones experience a range of surface strains which are a measure of displacement induced by mechanical loading. It is, therefore, desirable to develop an efficient, yet accurate, model in which the mechanical loading of MC3 is obtained via the induced displacement and strains. In this study, the ability of ANN to predict the compressive loading of equine MC3 bones was investigated and discussed. Nine hydrated MC3 bones from thoroughbred horses were loaded in compression in an MTS machine. Recordings of experiments including six components of surface strains, total displacement of the bones, the rate of loading, as well as horse age and bone side (left or right limb) were used as input variables of the ANN. It was demonstrated that the proposed method can provide a promising outcome for the prediction of load (R2≥0.98).