Open AccessThe development of the atherosclerosis diagnostic models under conditions of unbalanced classes
Author(s) -
Мария Владиславовна Демченко,
И. Л. Каширина
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1479/1/012026
Subject(s) - sensitivity (control systems) , machine learning , computer science , set (abstract data type) , artificial intelligence , engineering , programming language , electronic engineering
The main purpose of this study is to identify, using various methods of machine learning, the most effective markers of atherosclerosis and their main predictors, which can accurately determine the risk of this disease in the human body. In this study, various models and balancing techniques of the initial data set were used, which allowed us to develop the efficient classifiers according to the criteria of sensitivity, specificity and ROC AUC.