Menggunakan Metode Machine Learning Untuk Klasifikasi Pneumonia dari Citra X-Ray: Studi Perbandingan Model Klasifikasi

Authors

Ichtiar Akbar Sakti Universitas Nusa Mandiri

DOI:

Abstract

Pneumonia adalah penyakit pernapasan yang masih menjadi salah satu penyebab kematian teratas, terutama di negara-negara terbelakang. Diagnosis dini sangat penting, tetapi interpretasi manusia terhadap gambar rontgen dada menghadirkan kesulitan, terutama di daerah dengan tenaga medis yang minim. Tujuan dari penelitian ini adalah untuk menguji efektivitas beberapa algoritma pembelajaran mesin untuk mengkategorikan gambar rontgen dada menjadi dua kategori: pneumonia dan normal. Kumpulan data diperoleh dari Kaggle dan kemudian diproses terlebih dahulu dan diekstraksi fitur menggunakan Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), dan Gabor Filters. Enam metode pembelajaran mesin diuji: SVM, Regresi Logistik, K-Nearest Neighbors (KNN), Random Forest, Decision Tree, dan Naive Bayes. Kinerja dievaluasi menggunakan kriteria seperti akurasi, presisi, recall, F1-score, dan ROC-AUC. Hasilnya menunjukkan bahwa SVM dan Regresi Logistik memiliki akurasi terbesar (97% dengan AUC 1,00). KNN dan Random Forest menyusul dengan akurasi masing-masing 96% dan 94%. Sebagai perbandingan, Decision Tree dan Naive Bayes kurang berhasil. Temuan ini menunjukkan bahwa algoritma pembelajaran mesin berdasarkan ekstraksi fitur buatan tangan dapat menjadi alat yang efisien dan akurat untuk mendeteksi pneumonia secara otomatis dari gambar rontgen dada, terutama di lingkungan layanan kesehatan dengan akses terbatas ke teknologi modern.

Kata Kunci: Ekstraksi Fitur, Klasifikasi Gambar, Pembelajaran Mesin, Pneumonia, Sinar-X

References

[1] G. R. Ferreira and I. P. Marangoni, “Hospital morbidity and mortality profile due to pneumonia in Brazil between 2010 and 2020,” in II INTERNATIONAL SEVEN MULTIDISCIPLINARY CONGRESS, Seven Congress, Aug. 2023. doi: 10.56238/homeinternationalanais-080.

[2] J. Tomys-Składowska et al., “Pneumonia in Geriatric Patients: Focus on Etiology, Clinical Features, Diagnosis, and Prevention,” J. Health Study Med., vol. 2023, no. 1, pp. 375–398, Jan. 2023, doi: 10.2478/jhsm-2023-0017.

[3] Unit of Scientific Research, Applied College, Qassim University, Buraydah, Saudi Arabia, I. Imène, Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia, and A. Selmi, “Modelling of Neutrosophic Set-Based k-Nearest Neighbors Classifier for Virus Pneumonia and COVID-19 Recognition,” Int. J. Neutrosophic Sci., vol. 25, no. 1, pp. 64–74, 2025, doi: 10.54216/IJNS.250105.

[4] S. R. Howie, D. H. Hamer, and S. M. Graham, “Pneumonia.” International Encyclopedia of Public Health, 2020.

[5] A. K. Asok and L. L. Thampi, “Automated Diagnosis of Covid-19 and Pneumonia Using Transfer Learning and Custom Segmentation on Chest X-Ray Images,” WSEAS Trans. Comput. Res., vol. 12, pp. 328–335, Jun. 2024, doi: 10.37394/232018.2024.12.32.

[6] R. Castellano Ontiveros, M. Elgendi, and C. Menon, “A machine learning-based approach for constructing remote photoplethysmogram signals from video cameras,” Commun. Med., vol. 4, no. 1, p. 109, Jun. 2024, doi: 10.1038/s43856-024-00519-6.

[7] G. M. Raj, S. Dananjayan, and K. K. Gudivada, “Applications of artificial intelligence and machine learning in clinical medicine: What lies ahead ?,” Med. Adv., vol. 2, no. 2, pp. 202–204, Jun. 2024, doi: 10.1002/med4.62.

[8] S. Jasthy, K. Ramasubramanian, R. Vangipuram, and S. Bollu, “Comparative Analysis of Machine-Learning Algorithms for Accurate Diagnosis of Lung Diseases Using Chest X-ray Images: A Study on Balanced and Unbalanced Data on Segmented and Unsegmented Images,” Cureus, Jan. 2024, doi: 10.7759/cureus.53282.

[9] R. T. Sousa, O. Marques, F. A. A. M. N. Soares, I. I. G. Sene, L. L. G. De Oliveira, and E. S. Spoto, “Comparative Performance Analysis of Machine Learning Classifiers in Detection of Childhood Pneumonia Using Chest Radiographs,” Procedia Comput. Sci., vol. 18, pp. 2579–2582, 2013, doi: 10.1016/j.procs.2013.05.444.

[10] M. Mujahid et al., “Pneumonia detection on chest X-rays from Xception-based transfer learning and logistic regression,” Technol. Health Care, vol. 32, no. 6, pp. 3847–3870, Nov. 2024, doi: 10.3233/THC-230313.

[11] Q. An, W. Chen, and W. Shao, “A Deep Convolutional Neural Network for Pneumonia Detection in X-ray Images with Attention Ensemble,” Diagnostics, vol. 14, no. 4, p. 390, Feb. 2024, doi: 10.3390/diagnostics14040390.

[12] A. Prastyo, S. Sutikno, and K. Khadijah, “Improving support vector machine and backpropagation performance for diabetes mellitus classification,” Comput. Sci. Inf. Technol., vol. 5, no. 2, pp. 140–149, Jul. 2024, doi: 10.11591/csit.v5i2.pp140-149.

[13] H. J. Shin, E. H. Lee, K. Han, L. Ryu, and E.-K. Kim, “Development of a new prognostic model to predict pneumonia outcome using artificial intelligence-based chest radiograph results,” Sci. Rep., vol. 14, no. 1, p. 14415, Jun. 2024, doi: 10.1038/s41598-024-65488-1.

[14] R. Aldamani, D. A. Abuhani, and T. Shanableh, “LungVision: X-ray Imagery Classification for On-Edge Diagnosis Applications,” Algorithms, vol. 17, no. 7, p. 280, Jun. 2024, doi: 10.3390/a17070280.

[15] N. S. Fatimah and S. Agustin, “Klasifikasi Citra Batik Menggunakan Local Binary Pattern (LBP) dan Support Vector Machine (SVM),” vol. 22, no. 1, 2025.

[16] Department of Computer Engineering, Faculty of Engineering, Halic University, Istanbul, Turkey and M. S. Khalil, “Deducting Abnormalities in Chest X-Rays using Gabor Filters and Deep Neural Network (DNN),” J. Kejuruter., vol. 36, no. 5, pp. 1965–1972, Sep. 2024, doi: 10.17576/jkukm-2024-36(5)-16.

[17] N. Alangari and R. Alturki, “Predicting Students Final GPA using 15 Classiﬁcation Algorithms”.

[18] E. Demirović and P. J. Stuckey, “Optimal Decision Trees for Nonlinear Metrics,” Proc. AAAI Conf. Artif. Intell., vol. 35, no. 5, pp. 3733–3741, May 2021, doi: 10.1609/aaai.v35i5.16490.

[19] R. Natras, B. Soja, and M. Schmidt, “Ensemble Machine Learning of Random Forest, AdaBoost and XGBoost for Vertical Total Electron Content Forecasting,” Remote Sens., vol. 14, no. 15, p. 3547, Jul. 2022, doi: 10.3390/rs14153547.

[20] A. Razaque, M. Ben Haj Frej, M. Almi’ani, M. Alotaibi, and B. Alotaibi, “Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification,” Sensors, vol. 21, no. 13, p. 4431, Jun. 2021, doi: 10.3390/s21134431.

[21] L. Hakim, A. Sobri, L. Sunardi, and D. Nurdiansyah, “Prediksi penyakit jantung berbasis mesin learning dengan menggunakan metode k-nn,” vol. 07, no. 02, 2024.

[22] M. I. Ghozali, W. H. Sugiharto, and A. F. Iskandar, “Analisis Sentimen Pinjaman Online Di Media Sosial Twitter Menggunakan Metode Naive Bayes”.

[23] M. Turkoglu, “COVIDetectioNet: COVID-19 diagnosis system based on X-ray images using features selected from pre-learned deep features ensemble,” Appl. Intell., vol. 51, no. 3, pp. 1213–1226, Mar. 2021, doi: 10.1007/s10489-020-01888-w.

[24] J. N. Hasoon et al., “COVID-19 anomaly detection and classification method based on supervised machine learning of chest X-ray images,” Results Phys., vol. 31, p. 105045, Dec. 2021, doi: 10.1016/j.rinp.2021.105045.

[25] A. C. Muhammad, B. Engg, and M. Engg, “Dasar-dasar Pembelajaran Mesin”.

[26] R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, “An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review,” Information, vol. 15, no. 4, p. 235, Apr. 2024, doi: 10.3390/info15040235.