Application of knowledge discovery process on the prediction of stroke

Highlights • We predicted the outcome of stroke using knowledge discovery process (KDP) methods, Artificial Neural Networks (ANN) and Support Vector Machine (SVM) models. • The performance of the models, assessed as accuracy and area under curve (AUC), for predicting stroke was 85.9% and 0.928 for A...

Full description

Saved in:
Bibliographic Details
Published in:Computer methods and programs in biomedicine 2015-05, Vol.119 (3), p.181-185
Main Authors: Colak, Cemil, Karaman, Esra, Turtay, M. Gokhan
Format: Article
Language:English
Subjects:
Adult
Aged
Artificial neural networks (ANN)
Case-Control Studies
Data Mining - statistics & numerical data
Female
Humans
Internal Medicine
Knowledge discovery process (KDP)
Male
Middle Aged
Neural Networks (Computer)
Other
Predictive Value of Tests
Risk Factors
Stroke
Stroke - diagnosis
Stroke - etiology
Support vector machine (SVM)
Support Vector Machine - statistics & numerical data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • We predicted the outcome of stroke using knowledge discovery process (KDP) methods, Artificial Neural Networks (ANN) and Support Vector Machine (SVM) models. • The performance of the models, assessed as accuracy and area under curve (AUC), for predicting stroke was 85.9% and 0.928 for ANN, and 84.62% and 0.91 for SVM, respectively. • KDP was used for providing better understanding of the stroke data, and reducing unnecessary processes to be performed. • The proposed ANN model predicted successfully the stroke disease based on the selected predictors.
ISSN:0169-2607
1872-7565
DOI:10.1016/j.cmpb.2015.03.002