A new neural network method for peripheral vestibular disorder recognition using VNG parameter optimisation

Abstract

The peripheral vestibular disorder (VD) diagnosis is a required task to ensure the efficiency of the treatment that needs complementary examinations of vertigo. In clinical practice, different tests of videonystagmographic (VNG) technique are used to detect the presence of vestibular dysfunction disease. The topographical diagnosis of this disease presents a large diversity in its characteristics that show a mixture of problems for usual etiological analysis methods. In this paper, we propose an automatic classification method of VD by analysing and reducing the VNG parameters based on a determined criterion. Therefore, a multilayer neural network (MNN) classifier is applied for VNG dataset based on the fundamental measurements of normal and patients affected by VD. The experimental results confirm that the proposed approach is very interesting and helpful for an accurate diagnostic of this disease.