Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal BIOS : Jurnal Teknologi Informasi dan Rekayasa Komputer
Agustina, Alviani Rodyatul
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search

 1 
Sistem Deteksi Dini Diabetes Melitus Dengan Teknik Klasifikasi Algoritma C4.5 Berdasarkan Rekam Medis di RS Tk. III Baladhika Husada Jember Agustina, Alviani Rodyatul; Pratama, Mudafiq Riyan; Yunus, Muhammad; Rachmawati, Ervina
BIOS : Jurnal Teknologi Informasi dan Rekayasa Komputer Vol 7 No 1 (2026): March
Publisher : Puslitbang Sinergis Asa Professional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37148/bios.v7i1.203

Abstract

Diabetes Mellitus (DM) is a chronic disease condition that occurs when the pancreas cannot produce insulin or when the body cannot use insulin effectively. At Baladhika Husada Jember Hospital, DM ranks among the top 10 diseases with the highest mortality rate of 6.99% in 2024. In efforts to prevent and control DM, a website-based early detection system was developed using the C4.5 algorithm classification technique with the Waterfall method. The research stages included creating C4.5 algorithm classification rules using RapidMiner tools, followed by development using the Waterfall method, which consists of the communication, planning, modeling, construction, and deployment stages. The classification rules were developed using preprocessed data from a total of 240 datasets, resulting in 172 clean datasets obtained from medical records at Baladhika Husada Jember Hospital. The training and testing data ratio was 50:50 using stratified sampling. Performance testing using the Confusion Matrix method yielded accuracy, precision, and recall values of 100% each, along with 8 classification rules that were subsequently implemented in the system. Based on the research results, random blood sugar is the most influential risk factor for DM, as it achieved the highest gain ratio. Recommendations for future researchers include increasing the amount of data and expanding the variety of data to help the system learn more complex patterns.
Co-Authors Muhammad Yunus Pratama, Mudafiq Riyan Rachmawati, Ervina