Nerve graft selection for peripheral nerve regeneration using neural networks trained by a hybrid ACO/PSO method

Identification of the most successful strategy for applications in tissue engineering is often confusing, with a wide variety of options and variables available, that can fit into an ideal graft or scaffold. The complexity of the problem is multifold in application of grafts for regeneration of peripheral nerve injuries, with many variables that affect the regeneration process and thereby the success of regeneration. Here, we develop a Swarm Intelligence based artificial neural network (SWIRL) to predict the outcome of success of a nerve graft, thus providing critical information on the ability of a nerve graft to succeed under certain circumstances. Over 30 independent variables were identified and used as features for training the network and estimation of outcomes. Specific parameters such as the critical regeneration length and the ratio of the actual length to critical length were used in the evaluation and estimation of the success of the nerve grafts. Using the SWIRL, we estimate the success of regeneration of any nerve grafts to approximately 92.59 % accuracy. This system could allow for the estimation of the best possible outcome with a fixed set of variables or identification of best possible combinations with the multitude of options available, aiding researchers to perform experiments and test hypothesis efficiently and ethically.