Artificial neural network investigation of injectability and percolation of highly filled β -Tricalcium phosphate suspensions

Abstract

Over the past few decades, calcium phosphate cement has been used successfully for bone reconstruction applications. As percutaneous surgical methods have developed, there is an increased interest in calcium phosphate cement injection behavior. The aim of this study is to minimize percolation (liquid phase migration under pressure) and maximize injectability (ratio of the extruded part to whole) of highly filled β-tri calcium phosphate (β-TCP) suspensions by varying capillary flow process parameters with an artificial neural network (ANN) approach. The effects of hydroxyethyl cellulose (HEC) and polyethylene glycol (PEG-400) were also studied as binder additives for injectable β-tri calcium phosphate pastes. Prepared suspensions were investigated by capillary and small amplitude oscillatory rheometry. The study predicted experimental input and output data by using Backpropagation Neural networks via the Levenberg-Marquardt algorithm. The ANN model was developed by feed-forward back propagation network and predict percolation (%) and injectability (%). A great agreement was observed between the predicted values by the ANN model and the experimental data for injectability (%) and percolation (regression coefficients) of 0.9984 and 0.9982 respectively. The results depict that ANNs can improve the accuracy of injectability and percolation results which can be used to optimize process and additive parameters for injectable bone cements and pastes. 2 wt% HEC was determined as the most effective factor to improve the rheological properties of highly filled β-TCP pastes which could be injected as much as 99.21 % at a rate of 15 mm/min through dies with L/D ratio of 15. Their percolation value was calculated as 0.82 %. Lubricative effect of PEG-400 additive with 2 wt% HEC to reduce injection force was also demonstrated.