An artificial intelligent approach based human tibia fracture healing diagnosis using DC electrical stimulation, a technique to be used by orthopedists both for bone fracture treatment and also healing assessment, is described. Electrical data recorded across 20 different tibia fracture patients whose fracture site was stabilized using Teflon coated rings and a DC input voltage of 0.7 V was applied via K-wires were used to train the networks. The novel element is the data processing, which incorporates neural network and Adaptive Neuro Fuzzy Inference System (ANFIS) for estimating the fracture reunion is demonstrated in 20 patients. The ANFIS model was developed using least square method and gradient descent method having 32 Gaussian membership functions. The performance of ANFIS model developed was evaluated in terms of training epochs, prediction accuracy and absolute error in healing prediction. ANFIS Relative Absolute Error (RAE) was Zero. The performance evaluation shows ANFIS us a better diagnostic to an orthopedic surgeon for the fracture reunion prediction. © 2016 TSI® Press.