Classification of Normal and Abnormal Lung Conditions Using the Random Forest Method
DOI:
https://doi.org/10.54706/senastindo.v7.2025.418Keywords:
Lung classification, Random Forest, Respiratory Dataset, Machine Learning, Medical DiagnosisAbstract
Lung diseases are among the leading causes of mortality worldwide, significantly affecting human health
and quality of life. Early and accurate classification of lung conditions is crucial for supporting effective
medical diagnosis and treatment. This study aims to classify normal and abnormal lung conditions—
particularly asthma—using the Random Forest algorithm based on physiological features obtained from
the Respiratory Dataset provided by PhysioNet. The dataset consists of six main respiratory parameters:
Pressure (cmH₂O), Flow (L/s), V_tidal (L), Chest (mm), Abd (mm), and Global Aeration, which represent
the physiological characteristics of breathing activity. Data were divided into 80% for training and 20%
for testing, and the model was validated using 5-Fold Cross Validation to ensure stability and
generalization. The Random Forest model, built with 100 decision trees, achieved a classification accuracy
of 99.40%, with an F1-score of 0.9898, recall of 0.9883, and precision of 0.9913. These results indicate that
the Random Forest algorithm is highly effective in distinguishing between normal and abnormal lung
conditions. The study concludes that this method can serve as a foundation for developing intelligent, non
invasive medical decision-support systems that assist healthcare professionals in detecting respiratory
diseases quickly, accurately, and efficiently.
Downloads
References
[1] D. C. J. Kartikasari and A. Komputika, “Perbandingan Klasifikasi Penyakit Kanker
Paru-Paru Menggunakan Decision Tree Dan Random Forest Comparison Of Lung
Cancer Classification Using Decision Tree And Random Forest Komputika: Jurnal
Sistem Komputer,” J. Sist. Komput., vol. 14, no. 1, pp. 79–5, 2025, doi:
10.34010/kp5h2h96.
[2] H. Apriningsih et al., “Peningkatan Pengetahuan Petugas Kesehatan Mengenai Peran
Spirometri Sebagai Alat Deteksi Dini Penyakit Paru Obstruktif Kronik ( PPOK ) di
Fasilitas Kesehatan Layanan Primer,” vol. 4, no. 1, pp. 28–37, 2024.
[3] P. Penyakit, P. Obstruktif, and K. Ppok, “Jurnal Kesehatan,” vol. 11, pp. 31–40, 2022.
[4] A. S. Wahdah et al., “Tinjauan Pustaka : Risiko Kanker Paru pada Pasien dengan
Riwayat Tuberculosis Paru dan Penyakit Paru Obstruktif Kronik ( PPOK ) Article
Review : Risk of Lung Cancer in Patients with History of Pulmonary Tuberculosis and
Chronic Obstructive Pulmonary Disea,” vol. 14, no. 1, pp. 1845–1850, 2024.
[5] T. Indira et al., “Hubungan Perilaku Merokok Terhadap Kualitas Hidup Pasien Penyakit
Paru Obstruktif Kronis ( PPOK ) The Relationship between Smoking and the Quality of
Life of COPD Patients Abstract Pendahuluan Penyakit Paru Obstruktif Kronis ( PPOK )
atau disebut juga den,” vol. 9, no. 1, pp. 47–54, 2023.
[6] Z. A. Leleury and B. P. Tomasouw, “Diagnosa Penyakit Saluran Pernapasan Dengan
Menggunakan Support Vector Machine (Svm),” BAREKENG J. Ilmu Mat. dan Terap.,
vol. 9, no. 2, pp. 109–119, 2015, doi: 10.30598/barekengvol9iss2pp109-119.
[7] D. Kurniawan, M. Wahyudi, L. Pujiastuti, and S. Sumanto, “Deteksi dan Prediksi
Cerdas Penyakit Paru-Paru dengan Algoritma Random Fores,” Indones. J. Comput. Sci.,
vol. 3, no. 1, pp. 51–56, 2024, doi: 10.31294/ijcs.v3i1.6071.
[8] F. Ramadhani, H. Syahputra, R. L. Simanjuntak, T. R. Siagian*, U. Nisa, and V.
Anggraini, “Klasifikasi Suara Paru Normal Dan Abnormal Berbasis Algoritma CNN
(Convolutional Neural Network),” J. Teknol. Inf. dan Terap., vol. 11, no. 1, pp. 15–20,
2024, doi: 10.25047/jtit.v11i1.370.
[9] N. Selayanti, S. A. Putri, M. Kristanaya, M. P. Azzahra, M. G. Navsih, and K. M.
Hindrayani, “Penerapan Machine Learning Algoritma Random Forest Untuk Prediksi
Penyakit Jantung,” Pros. Semin. Nas. Sains Data, vol. 4, no. 1, pp. 895–906, 2024, doi:
10.33005/senada.v4i1.376.
[10] P. Ngalle and K. Takalar, “Arus Jurnal Sains dan Teknologi ( AJST ) Analisa Diagnosa
Penyakit Berdasarkan Riwayat Medis menggunakan Algoritma Random Forest Studi
Kasus Rumah Sakit,” vol. 2, no. 2, 2024.
[11] S. G. Bollmeier and A. P. Hartmann, “Management of chronic obstructive pulmonary
disease: A review focusing on exacerbations,” Am. J. Heal. Pharm., vol. 77, no. 4, pp.
259–268, 2020, doi: 10.1093/ajhp/zxz306.
[12] Guy, E. F. S., Clifton, J. A., Caljé-van der Klei, T., Chen, R., Knopp, J., Moeller, K., &
Chase, J. G. (2023). Respiratory dataset from PEEP study with expiratory occlusion
(version 1.0.0). PhysioNet. RRID:SCR_007345. https://doi.org/10.13026/d767-e709
[13] Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... &
Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a
new research resource for complex physiologic signals. Circulation [Online]. 101 (23),
pp. e215–e220. RRID:SCR_007345.
[14] A. Achmad, A. Adnan, and M. Rijal, “Klasifikasi Penyakit Pernapasan Berbasis
Visualisasi Suara Menggunakan Metode Support Vector Machine,” Jurnal Ilmiah Ilmu
Komputer, vol. 8, no. 2, pp. 115–119, Sep. 2022, Fakultas Ilmu Komputer, Universitas Al
Asyariah Mandar.
[15] N. S. Wibisono, S. A. Wicaksono, and N. Y. Setiawan, “Klasifikasi Donatur pada Yayasan Jajan Pahala Menggunakan Algoritma Random Forest,” Jurnal Pengembangan Teknologi
Informasi dan Ilmu Komputer, vol. 1, no. 1, pp. 1–9, Jan. 2017.
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2025 Rama Nanda, Putri Ica Rahmiatun, Ninda Cahya Noprianingrum, Agrippina Alodia Yusuf, Muhammad Iman Dinata
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
