ENSEMBLE SOFT VOTING DARI MODEL HYBRID CNN-TRANSFER LEARNING UNTUK KLASIFIKASI PENYAKIT PARU-PARU (STUDI KASUS RSUD MARIA WALANDA MARAMIS)
Isi Artikel Utama
Abstrak
Penyakit paru-paru seperti tuberkulosis, bronkitis, dan pneumonia masih menjadi masalah kesehatan serius di Indonesia dengan angka kematian yang tinggi. Di Sulawesi Utara, RSUD Maria Walanda Maramis menghadapi tantangan dalam diagnosis dini karena keterbatasan tenaga medis spesialis dan beban kerja yang tinggi. Penelitian ini bertujuan mengembangkan model ensemble soft voting dari hybrid Convolutional Neural Network (CNN) dan transfer learning untuk meningkatkan akurasi klasifikasi penyakit paru-paru menggunakan citra X-ray dada. Metode yang diusulkan menggabungkan tiga model berbeda yaitu VGG16, MobileNetV2, dan CNN custom melalui teknik soft voting ensemble. Dataset terdiri dari 589 citra X-ray pasien RSUD Maria Walanda Maramis yang telah diberi label oleh ahli radiologi. Evaluasi menggunakan 5-fold cross validation menunjukkan bahwa model ensemble mencapai akurasi 75.44%, precision 75.12%, recall 75.44%, dan F1-score 74.88%, lebih tinggi dibandingkan model individual terbaik (MobileNetV2 dengan akurasi 71.93%). Analisis statistik menggunakan uji McNemar membuktikan perbedaan signifikan secara statistik antara model ensemble dan model individual. Hasil penelitian ini menunjukkan potensi sistem berbasis kecerdasan buatan sebagai alat bantu diagnosis untuk mendukung tenaga medis dalam meningkatkan ketepatan dan kecepatan diagnosis penyakit paru-paru di fasilitas kesehatan dengan sumber daya terbatas.
Rincian Artikel
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright (c) STMIK TIMEReferensi
[1] Kementerian Kesehatan Republik Indonesia, “Laporan Program Penanggulangan Tuberkulosis Tahun 2022.” Kementerian Kesehatan RI, Sept. 2023. [Online]. Available: https://www.tbindonesia.or.id/wp-content/uploads/2023/09/Laporan-Tahunan-Program-TBC-2022.pdf
[2] Dinas Kesehatan Provinsi Sulawesi Utara, “Laporan Kinerja Instansi Pemerintah Tahun 2025.” Dinas Kesehatan Provinsi Sulawesi Utara, Feb. 27, 2025. [Online]. Available: https://dinkes.sulutprov.go.id/l-content/uploads/KINERJA_DINKES/Kinerja_2024/LKIP_2024.pdf
[3] K. Ferry Dwi, S. Dianova, and R. Rinaldy, “Analisis Keterlambatan Diagnosis dan Terapi Kanker Paru Di RSUD Dr. Zainoel Abidin, Banda Aceh,” J. Med. Sci., vol. 5, no. 1, pp. 1–7, July 2024, doi: 10.55572/jms.v5i1.107.
[4] Muazzez Buket Darici, M. B. Darici, Zümray Dokur, Z. Dokur, Tamer Ölmez, and T. Ölmez, “Pneumonia Detection and Classification Using Deep learning on Chest X-Ray Images,” Int. J. Intell. Syst. Appl. Eng., vol. 8, no. 4, pp. 177–183, 2020, doi: 10.18201/ijisae.2020466310.
[5] Global Programme on Tuberculosis and Lung Health (GTB), and Tuberculosis Vaccine Accelerator Council, “Global tuberculosis report 2022.” World Health Organization, Oktober 2022. [Online]. Available: https://www.who.int/publications/i/item/9789240061729
[6] C. Randieri, A. Perrotta, A. Puglisi, M. Grazia Bocci, and C. Napoli, “CNN-Based Framework for Classifying COVID-19, Pneumonia, and Normal Chest X-Rays,” Big Data Cogn. Comput., vol. 9, no. 7, p. 186, July 2025, doi: 10.3390/bdcc9070186.
[7] M. Chihaoui, N. Dhibi, and A. Ferchichi, “Optimization of Convolutional Neural Network and visual geometry group-16 using genetic algorithms for pneumonia detection,” Front. Med., vol. 11, p. 1498403, Dec. 2024, doi: 10.3389/fmed.2024.1498403.
[8] B. Nugroho and E. Y. Puspaningrum, “Kinerja Metode CNN untuk Klasifikasi Pneumonia dengan Variasi Ukuran Citra Input,” J. Teknol. Inf. Dan Ilmu Komput., vol. 8, no. 3, pp. 533–538, June 2021, doi: 10.25126/jtiik.2021834515.
[9] A. Rama, M. Rajakumar, N. Mythili, S. Arunmozhi, M. Mohammed, and V. Rajinikanth, “Detection of TB from Chest X-ray: A Study with EfficientNet,” 2023 Int. Conf. Syst. Comput. Autom. Netw. ICSCAN, 2023, doi: 10.1109/icscan58655.2023.10395301.
[10] O. Iparraguirre-Villanueva, V. Guevara-Ponce, O. R. Paredes, F. Sierra-Liñan, J. Zapata-Paulini, and M. Cabanillas-Carbonell, “Convolutional Neural Networks with Transfer learning for Pneumonia Detection,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 9, 2022, doi: 10.14569/IJACSA.2022.0130963.
[11] X. Liu, Z. Yu, and L. Tan, “Deep learning for Lung Disease Classification Using Transfer learning and a Custom ized CNN Architecture with Attention,” 2024, arXiv. doi: 10.48550/ARXIV.2408.13180.
[12] Tawsifur Rahman et al., “Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization,” IEEE Access, vol. 8, Oct. 2020, doi: 10.1109/access.2020.3031384.
[13] N. Agustina and C. N. Ihsan, “Pendekatan Ensemble untuk Analisis Sentimen Covid19 Menggunakan Pengklasifikasi Soft Voting,” J. Teknol. Inf. Dan Ilmu Komput., vol. 10, no. 2, pp. 263–270, Apr. 2023, doi: 10.25126/jtiik.20236215.
[14] Alhassan Mabrouk et al., “Pneumonia Detection on Chest X-ray Images Using Ensemble of Deep Convolutional Neural Networks,” Appl. Sci., vol. 12, no. 13, pp. 6448–6448, June 2022, doi: 10.3390/app12136448.
[15] A. Munandar, W. Maulana Baihaqi, and A. Nurhopipah, “A Soft voting ensemble Classifier to Improve Survival Rate Predictions of Cardiovascular Heart Failure Patients,” Ilk. J. Ilm., vol. 15, no. 2, pp. 344–352, Aug. 2023, doi: 10.33096/ilkom.v15i2.1632.344-352.
[16] Rana Jassim Mohammed et al., “A Robust Hybrid Machine and Deep Learning-based Model for Classification and Identification of Chest X-ray Images,” Eng. Technol. Amp Appl. Sci. Res., 2024, doi: 10.48084/etasr.7828.
[17] Rasuri Harshitha, Mudu Navya Sree, G. K. Kumar, M. Anila, and S. C. Ramu, “Enhanced Pneumonia Detection in Chest X-Rays Through a Hybrid DL-ML Ensemble Model,” 2025 3rd Int. Conf. Intell. Data Commun. Technol. Internet Things IDCIoT, 2025, doi: 10.1109/idciot64235.2025.10915114.