Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Rozzi Kesuma Dinata
Malikussaleh University
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
PERBANDINGAN METODE LOGISTIC REGRESSION DAN RANDOM FOREST DALAM KLASIFIKASI PENYAKIT KULIT MULTIKELAS: COMPARISON OF LOGISTIC REGRESSION AND RANDOM FOREST METHODS IN MULTICLASS SKIN DISEASE CLASSIFICATION Syatriani Jauhari; Rozzi Kesuma Dinata; Ar Razi
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 10 No 2 (2025): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v10i2.6551

Abstract

This study compares two classification algorithms, namely Logistic Regression and Random Forest, in classifying eight types of skin diseases based on ten clinical symptoms. The data used consists of 271 patient medical records from Cut Meutia General Hospital, which are divided into 80% training data and 20% test data. The pre-processing stage included imputing missing data, encoding categorical variables, and normalizing numerical features for the Logistic Regression model. Both algorithms were implemented using the Scikit-learn library in the Python programming language. Evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results show that Logistic Regression achieved an accuracy of 94.55%, slightly higher than Random Forest, which reached 92.73%. Validation using 5-fold cross-validation and a paired t-test yielded a p-value of 0.0371, indicating that the performance difference between the two models is statistically significant. However, limitations such as the relatively small amount of data and class imbalance impacted the low performance of the model in minority categories such as Psoriasis. This study is expected to serve as a foundation for the development of data-based medical diagnosis assistance systems to improve efficiency and accuracy in healthcare services.
Co-Authors Ar Razi Syatriani Jauhari