Ensemble methods for solving problems of medical diagnosis

Abstract

A consolidating method for analyzing series of observations based on a fitted model of a mixture of catalysts of the main components is proposed, which makes it possible to study any number of markers. Contrasting the longitudinal approach, it eliminates the need to connect regression analysis methods with their own uncertainties when choosing particular models. The consolidating method allows obtaining an original result in the subject area of early diagnosis of a disease: all options for using markers demonstrate an increase in classification accuracy with an increase in the length of a series of examinations.