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
Yunitasari, Arleni Aulia
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 Mellitus Berdasarkan Rekam Medis Menggunakan Algoritma K-Nearest Neighbor Yunitasari, Arleni Aulia; Pratama, Mudafiq Riyan; Yunus, Muhammad; Suyoso, Gandu Eko Julianto
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.v7i1.204

Abstract

At RSD dr. Soebandi Jember, 51% of Diabetes Mellitus (DM) patients are diagnosed after complications occur, and DM is the third leading cause of death among non-communicable diseases, accounting for 13.6%. This situation indicates a high rate of delayed case identification. Delayed diagnosis significantly increases patient mortality and morbidity rates, emphasizing the urgent need for an effective, integrated early, and detection system. This study developed a web-based early detection system for DM using the K-Nearest Neighbor (K-NN) algorithm with the Waterfall development method, consisting of the stages of communication, planning, modeling, construction, and deployment. The data comprised from 342 inpatient medical records, and after preprocessing, 164 clean data were obtained with variables including age, gender, family history, blood pressure, random blood sugar, and body mass index. The data were split using stratified sampling (50:50), with K=5 value selected based on the best performance. Blackbox testing was conducted to ensure the system’s functionality, while performance testing compared the system’s classification results with the test data. The performance of the K-NN algorithm for DM detection was evaluated using a Confusion Matrix, resulting in an accuracy of 97.56%, precision of 100%, and recall of 95.83%, which were consistent with the results from the WEKA tool. This system is expected to serve as an early screening tool and support DM prevention efforts.
Co-Authors Muhammad Yunus Pratama, Mudafiq Riyan Suyoso, Gandu Eko Julianto