Big Data Analysis to Stroke Dataset Modeling
Big Data Analysis to Stroke Dataset Modeling
Author(s): Ivelin G. Ivanov, Tonya Mateva, Nely Baeva, Ivan IvanovSubject(s): Economy, Library and Information Science, Electronic information storage and retrieval, ICT Information and Communications Technologies
Published by: Институт за знание, наука и иновации ЕООД
Keywords: Classification Problem; Decision Tree Model; Anaconda; Python 3. 7
Summary/Abstract: This paper considers a model to analyze the stroke imbalanced dataset. The aim of the model is to increase the detection of stroke possibility through machine learning models. The model includes new extensions to Python commands, which ensure the higher efficiency of the built-in computer classification models. Python is an open-source language. The model is described as an algorithm that can be successfully applied when conducting analysis in medical datasets. The proposed Decision Tree model achieves higher accuracy, precision and sensitivity, specificity.
Journal: Сборник доклади от научна конференция „Знание, наука, иновации, технологии”
- Issue Year: 1/2023
- Issue No: 4
- Page Range: 483-490
- Page Count: 8
- Language: English
