Many-To-Many Linear-Feedback Shift Model for Training of Artificial Neural Network in Dentistry

In this paper, the authors consider how to label and save a large number of images that should be predict in a single file. Technique of automatic labeling the data set with finite element model for training of artificial neural network in tomography are proposed. Simple transparent example of sixteen images for predict in a single HDF5 file training of artificial neural network in tomography show accuracy 100% for training set as well for test set. Then this technique is able to build information model of salivary immune and periodontal status and to evaluate the correlation between salivary immunoglobulin level, inflammation in periodontal tissues and orthodontic pathology. The study was conducted on 139 subjects, which were in the age group of 12-18 years reporting to the Department of Pediatric Dentistry of Kharkiv National Medical University. The atopic group consisted of 103 patients with the following conditions: 76 patients of atopic diseases and gingivitis (Group 1) and 27 patients of atopic diseases, gingivitis and orthodontic pathology (Group 2). Among the 139 subjects, 36 healthy controls formed Group 3. The obtained data prove that there is an immune misbalance in children with atopy and in children with combined atopic and orthodontic pathology. Level of sIgA and IgG is decreased in group of patients with atopy and in group of children with atopic and orthodontic pathology. The information model of salivary immune and periodontal status was built and regression analysis showed that there was strong correlation between inflammation in periodontal tissues and level of immunoglobulins.