Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Perekam dan Informasi Kesehatan Imelda (JIPIKI)
Al Mubarok, Hafiddhudin
Unknown Affiliation
Health Professions Public Health

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

Found 1 Documents
Search
Journal : Jurnal Ilmiah Perekam dan Informasi Kesehatan Imelda (JIPIKI)

 1 
DATA MINING PENYAKIT TERBANYAK BERDASARKAN DECISION TREE ALGORITMA C4.5 DI RSUD PANDAN ARANG BOYOLALI Al Mubarok, Hafiddhudin; Sutrisno, Trismianto Asmo; Sugiarsi, Sri
Jurnal Ilmiah Perekam dan Informasi Kesehatan Imelda (JIPIKI) Vol. 10 No. 1 (2025): Jurnal Ilmiah Perekam dan Informasi Kesehatan Imelda Edisi Februari
Publisher : Akademi Perekam dan Informasi Kesehatan Imelda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52943/jipiki.v10i1.1512

Abstract

Top 10 disease data is data on diseases that often appear and occur most often. Data collection of the top 10 diseases is used to determine disease patterns in the community. Decision tree classification method is a model that maps observations of an item so that a conclusion is obtained about the target value of an item described in the form of a tree model. The C4.5 algorithm is method for creating a decision tree based on the training data that has been provided. The purpose of this research is to result in the classification of the most diseases based on the C4.5 decision tree algorithm of Pandan Arang Boyolali Hospital using excel and RapidMiner. This research design is descriptive observational. The data collection technique in this study was observation, with a total net data of 3449 data. The results of this research, there are no differences in results between excel and RapidMiner which results in the classification of the most diseases, which are blocks A00-B99, Z00-Z99, I00-I99, O00-O99, J00-J99, and E00-E90, and 18 rules are obtained. Evaluation of the performance of the C4.5 algorithm decision tree classification model using confusion matrix produces an accuracy value of 25.14%.
Co-Authors Sri Sugiarsi Trismianto Asmo Sutrisno