Open AccessMulticlass Classification in the Problem of Differential Diagnosis of Venous Diseases Based on Microwave Radiometry Data
Author(s) -
Vladislav Levshinskii
Publication year - 2021
Publication title -
programmnye sistemy: teoriâ i priloženiâ
Language(s) - English
Resource type - Journals
ISSN - 2079-3316
DOI - 10.25209/2079-3316-2021-12-2-37-52
Subject(s) - multiclass classification , computer science , feature (linguistics) , data mining , binary classification , pattern recognition (psychology) , logistic regression , multivariate statistics , differential (mechanical device) , artificial intelligence , support vector machine , machine learning , engineering , philosophy , linguistics , aerospace engineering
This article is devoted to applying mathematical models in the differential diagnosis of venous diseases based on microwave radiometry data. A modified approach for transforming feature space in thermometric data is described. After constructing features, a multiclass classification problem is solved in several ways: by reducing to binary classification problems using “one versus rest” and “one versus one” methods and building a multivariate logistic regression model. The best classification model achieved an average balanced accuracy score of 0.574. A key feature of the approach is that classification result can be explained and justified in terms understandable to a diagnostician. This article presents the most significant patterns in thermometric data and the accuracy with which they can identify different classes of diseases.