Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Catur Ari Setianto
Fakultas Kedokteran, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Sistem Pendukung Keputusan Diagnosis Penyakit Stroke menggunakan Metode Fuzzy K-Nearest Neighbor (FK-NN) (Studi Kasus Puskesmas Kendal Kerep Kota Malang) Yearra Taufan Ardy Rinaldy; Arief Andy Soebroto; Catur Ari Setianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 7 (2021): Juli 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Stroke constitute disease that can cause death and disablement, but the number of patient is still very high. So that new stroke cases do not continue to grow, needed a way for early detection of stroke risk so that people who have the potential to suffer a stroke can take preventative. However, stroke is a complex disease that shows different symptoms between one patient and another. Moreover, the cause of stroke between one person and another person can also be different so that early detection of possible risk of stroke in a patient should be made with care.Decision support systems built using FK-NN are considered capable of assisting early detection of stroke risk quickly, thoroughly, and objectively.support system built with FK-NN will observe to stroke risk factors and calculate using framingham risk score, the method commonly used by doctors to calculate the risk of cardio vascular disease.The system then classifies data using the FK-NN method in the class of low risk stroke, moderate risk stroke, and high risk stroke. The results of this study indicate that the FK-NN is able to properly assist early detection of stroke risk, which resulting in an accuracy of 61.1% when K is 4 and the percentage of training data is 50% of the entire data set.
Co-Authors Arief Andy Soebroto Yearra Taufan Ardy Rinaldy