Factorial research and the recognition problem solution using the example of obstructive sleep apnea syndrome

Abstract

The article is devoted to the problem of identifying factors directly or indirectly influencing the presence of obstructive sleep apnea syndrome in patients (OSAS) and solving the problem of pattern recognition in the factor space using the example OSAS. A factorial study was carried out for each group of indicators characterizing the condition of patients with OSAS, optimal factor structures were formed and the interpretation of the identified latent-integrative factors was carried out. It was implemented Bayes’ formula for calculating probabilities by OSAS groups in factor space. It is proposed formula for the transition from initial data to factors for finding the n-dimensional distribution density which is necessary for solving problems of recognition and based on the Bayesian criterion. There are given the proof of the transition formula and computational algorithms for the recognition problem.