Application of statistical data analysis algorithms and determination of the most significant diagnostic factors

Abstract

The article examines the application of statistical data analysis algorithms in diagnostics and the identification of significant factors influencing observed phenomena. The use of statistical methods, such as multiple regression, logistic regression, and neural networks, is discussed. The study focuses on determining the most impactful factors, establishing relationships between variables, and evaluating the effectiveness of technologies and methods. The dataset, provided by Universidad Cardenal Herrera, CEU, Madrid, Spain, includes factors related to patients’ demographics, health conditions, and lifestyle. The analysis involves deductive analysis, correlation analysis, and Kohonen maps to identify relevant factors. Decision tree analysis is conducted using different combinations of factors, including average glucose levels and body mass index. The results show varying error rates for different methods and factor combinations. Overall, statistical data analysis demonstrates its potential for faster and more accurate identification of significant diagnostic factors.