Affiliations: [a] Near East University, Lefkosa, North Cyprus | [b] European Centre for Research and Academic Affairs (ECRAA), Lefkosa, Mersin 10, North Cyprus
Correspondence:
[*]
Corresponding author: O.K. Oyedotun, Near East University, Lefkosa, via Mersin-10, North Cyprus. E-mail:oyebade.oyedotun.k@ieee.org
Abstract: Artificial neural networks have found
applications in various areas of medical diagnosis. The capability of neural
networks to learn medical data, mining useful and complex relationships that
exist between attributes has earned it a major domain in decision support
systems. This paper proposes a fast automatic system for the diagnosis of
disk hernia and spondylolisthesis using biomechanical features and neural
network. Such systems as described within this work allow the diagnosis of
new cases using trained neural networks; patients are classified as either
having disk hernia, spondylolisthesis, or normal. Generally, both disk
hernia and spondylolisthesis present similar symptoms; hence, diagnosis is
prone to inter-misclassification error. This work is significant in that the
proposed systems are capable of making fast decisions on such somewhat
difficult diagnoses with reasonable accuracies. Feedforward neural network
and radial basis function networks are trained on data obtained from a
public database. The results obtained within this research are promising and
show that neural networks can find applications as efficient and effective
expert systems for the diagnosis of disk hernia and spondylolisthesis.
Keywords: Disk hernia, spondylolisthesis, biomechanical features, diagnosis, neural network
