Multi-class Classification Analysis for Predicting Medical Specialization Suitability Based on Raw Scores of 14 Clinical Clerkship Rotations Using Random Forest Algorithm
Keywords:
Random Forest, Educational Data Mining, Clinical Clerkships, Specialization Prediction, Multi-class Classification, Residency Program.Abstract
Inaccurate selection of Medical Specialist Education Programs (PPDS) in Indonesia is often rooted in subjective bias and the underutilization of historical student competency data. This phenomenon contributes to high resident dropout rates and long-term career dissatisfaction. This study aims to develop an Educational Data Mining (EDM) based decision support model capable of providing objective medical specialization recommendations. The research employs the Random Forest algorithm—an ensemble learning method—to classify 567 students into 7 specialization clusters based on raw scores (0-100) from 14 clinical clerkship rotations. Experimental results demonstrate that Random Forest effectively mitigates the overfitting issues common in single decision trees, achieving a testing accuracy of 97.36%. Furthermore, the results show a balanced distribution of recommendations, with Surgery and Internal Medicine emerging as dominant fields in accordance with clinical performance patterns. The outputs of this research include personalized recommendation lists and strategic statistical summaries for medical education institutions.
References
R. Fauziah, M. Pusparini, and E. M. Astiwara, “Hubungan Tingkat Stress Mahasiswa Dengan Hasil Kepaniteraan Klinik Pada Mahasiswa Fakultas Kedokteran Universitas Yarsi Angkatan 2016 Dan Pandangan Menurut Islam,” 2022.
A. Akbar Tambunan and R. Yulistika Utami, “PENELITIAN Hubungan Keterampilan Klinis dan Kesiapan Praktik Lulusan Dokter Fakultas Kedokteran UMSU,” vol. 4, no. 2, 2023.
N. * Risky, D. Setiyawan, D. Hermawan, and O. Herdiyanto, “Prediksi Kelulusan Mahasiswa Menggunakan Algoritma Decision Tree C4.5 Berbasis Data Akademik dengan Validasi 10-Fold,” vol. 6, no. 6, pp. 670–678, 2025, doi: 10.47065/tin.v6i6.8662.
N. Sinulingga, M. I. Sarif, N. A. Ramadhani, K. Nurfebia, and F. Y. Sulistia, “Penerapan Algoritma K-Means Clustering untuk Mengetahui Pola Peminjaman Buku di Perpustakaan Universitas Imelda Medan,” Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI), vol. 4, no. 3, pp. 1552–1560, Dec. 2025, doi: 10.62712/juktisi.v4i3.707.
J. Ma’sum, A. Febriani, and D. Rachmawaty, “PENERAPAN METODE KLASIFIKASI DECISION TREE UNTUK MEMPREDIKSI KELULUSAN TEPAT WAKTU,” Journal Of Industrial Engineering And Technology (Jointech) UNIVERSITAS MURIA KUDUS Journal homepage, vol. 2, no. 1, pp. 1–14, 2021, [Online]. Available: http://journal.UMK.ac.id/index.php/jointech
R. D. L. N. Karisma, U. Pagalay, and M. Khudzaifah, “Random Forest Classification of Infant Mortality Rate in Indonesia: A Gini-Based Analysis,” CAUCHY: Jurnal Matematika Murni dan Aplikasi, vol. 10, no. 2, pp. 644–659, Jul. 2025, doi: 10.18860/cauchy.v10i2.29508.
Z. Sitorus, M. Iqbal, D. Nasution, and R. Farta Wijaya, “Penerapan Deep Learning dan Analisis Sentimen terhadap Gap Kompetensi Lulusan Lembaga Pendidikan dan Pelatihan Vokasi terhadap Dunia Kerja dengan Metode Long Short-Term Memory (LSTM),” Bulletin of Information Technology (BIT), vol. 6, no. 2, pp. 161–172, 2025, doi: 10.47065/bit.v5i2.2029.
D. Apriandi, R. M. Sari, and M. I. Sarif, “Analisis Clustering Untuk Menentukan Siswa Berprestasi di SMK Swasta TI Panca Dharma Stungkit Menggunakan Metode K-Means,” Jurnal Minfo Polgan, vol. 13, no. 1, pp. 1117–1129, Aug. 2024, doi: 10.33395/jmp.v13i1.13959.
S. Maulana, A. Premana, and B. Irawan, “PREDIKSI PRESTASI AKADEMIK SISWA TERBAIK MENGGUNAKAN ALGORITMA DECISION TREE BERBASIS DATA HISTORIS,” 2025.
H. Andrianof, A. P. Gusman, and O. A. Putra, “Implementasi Algoritma Random Forest untuk Prediksi Kelulusan Mahasiswa Berdasarkan Data Akademik: Studi Kasus di Perguruan Tinggi Indonesia.”
T. Rizki Adiana and F. Sulianta, “Deteksi Dini Penyakit Diabetes Menggunakan Metode Decision Tree.” [Online]. Available: https://www.kaggle.com/datasets/uciml/pima-
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Abdul Chaidir Harahap, Muhammad Irfan Sarif
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
International Conference On Islamic Community Studies, Education and Science, its website, and the articles published therein are licensed under a 
