Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika
Nor, Reza Ummam Nor Ummam
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Web Design for Stroke Early Detection Using Decision Tree C5.0 Purwanti, Endah; Nor, Reza Ummam Nor Ummam; Soelistyono, Soegianto
Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika Vol 20, No 2 (2023): Komputasi: Jurnal Ilmiah Ilmu Komputer dan Matematika
Publisher : Ilmu Komputer, FMIPA, Universitas Pakuan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33751/komputasi.v20i2.8265

Abstract

Stroke is a disease that needs serious attention because it can cause disability and even death. According to World Health Organization (WHO) in 2022, stroke is the second leading cause of death and a leading cause of disability in the world. In Indonesia, stroke is the first leading of non-communicable disease proportion according to Riset Kesehatan Dasar in 2018. This study aims to design a web application that can help stroke early detection in a person so that people are more concerned about preventing a stroke. This study used Decision Tree (DT) C5.0 method by utilizing 10 stroke risk factors to analyze the risk of stroke in a person. Decision Tree method can break down complex datasets into several simple rules illustrated by a tree, hence the name Decision Tree. The DT C5.0 is one kind of Decision Tree method that has fast performance in classifying data compared to other methods. Therefore, this study observes how DT C5.0 works in detecting stroke risk. The output of this web application is a statement whether a person has a stroke risk or not. The secondary dataset used for model development totaled 5,109 data consisting of 249 stroke patient data and 4,860 non-stroke patient data. In this study, data balancing and cross validation were carried out so that the performance of the training results model was obtained, namely accuracy 83.54%, precision 78.67%, sensitivity 92.20%, and specificity 74.87%. Furthermore, the performance of the test results model is accuracy 84.42%, precision 79.26%, sensitivity 93.10%, and specificity 75.80%.
Co-Authors Soelistyono, Soegianto Solly Aryza