Comparative Analysis of Machine Learning Algorithms for Lung Cancer Classification: A Progressive Evaluation from Preprocessing to Hyperparameter Tuning

Laurentius Joandanu; Usman Sudibyo

doi:10.30871/jaic.v10i4.13523

Authors

Laurentius Joandanu Universitas Dian Nuswantoro
Usman Sudibyo Universitas Dian Nuswantoro

DOI:

https://doi.org/10.30871/jaic.v10i4.13523

Keywords:

Lung Cancer, Machine Learning, Preprocessing, Hyperparameter Tuning, Random Forest

Abstract

Lung cancer is one of the leading causes of cancer-related deaths worldwide, with the main challenge being the difficulty of diagnosis at an early stage. Machine learning-based approaches have been proven to provide efficient solutions in supporting the classification process of this disease. This study proposes a comparative study of five machine learning algorithms, namely K-Nearest Neighbors (KNN), Logistic Regression, Random Forest, CatBoost and LightBGM, for lung cancer classification using the survey_lung_cancer.csv dataset consisting of 309 instances and 16 clinical features. All models were trained using a comprehensive preprocessing pipeline including duplicate data removal, missing values handling, outlier handling using the Interquartile Range (IQR) method, and categorical feature encoding using One-Hot Encoding. Hyperparameter optimization was performed uniformly using RandomizedSearchCV with Stratified K-Fold (k=10) and 50 iterations to ensure a fair comparison between algorithms. Each algorithm was evaluated under three progressive modelling conditions: baseline, after preprocessing, and after hyperparameter tuning, to quantify the individual contribution of each stage to model performance. The results show that Random Forest consistently recorded the best performance across all modelling conditions with an accuracy of 0.9464 and F1-Score of 0.9684 after applying preprocessing and hyperparameter tuning, demonstrating the effectiveness of the proposed progressive preprocessing and hyperparameter tuning pipeline. Learning curve analysis proves that none of the models experienced significant overfitting on the dataset used, indicating stable performance that has yet to be validated on independent clinical data.

Downloads

Download data is not yet available.

References

[1] I. Buana and D. Agustian Harahap, “Asbestos, Radon Dan Polusi Udara Sebagai Faktor Resiko Kanker Paru Pada Perempuan Bukan Perokok,” 2022. doi: 10.29103/averrous.v8i1.7088.

[2] S. Mustofa et al., “Laporan Kasus Kanker Paru Kiri Jenis Adenokarsinoma Dengan Hemoptisis Non Masive [2023],” Jurnal Ilmu Kedokteran dan Kesehatan, May 2023, doi: 10.33024/jikk.v10i5.10085.

[3] S. Alfarisa, S. Wahyuni, and Efriza, “Karakteristik Pasien Kanker Paru di RSUP Dr. M. Djamil Padang Tahun 2021,” Scientific Journal, Nov. 2023, doi: 10.56260/sciena.v2i6.116.

[4] A. F. Hamdani, W. Purbaningsih, and W. Y. Nalapraya, “Karakteristik Demografi dan Klinikopatologi Pasien Kanker Paru di RSUD Al−Ihsan,” Jurnal Riset Kedokteran, pp. 97–102, Dec. 2023, doi: 10.29313/jrk.v3i2.2959.

[5] S. Salsabila, S. A. Intan, and D. W. Fitrina, “Gambaran Tipe Sel Kanker Paru Berdasarkan Usia, Jenis Kelamin, dan Paparan Rokok di RSUP Dr. M. Djamil Padang Tahun 2018-2020,” Jurnal Ilmu Kesehatan Indonesia, vol. 4, no. 4, pp. 281–288, Dec. 2023, doi: 10.25077/jikesi.v4i4.1118.

[6] S. Jiwandana Pinasthika, “Aplikasi Pembelajaran Mesin dalam Pengolahan Data Citra untuk Bidang Medis: Sebuah Kajian Pustaka,” Journal of Information Engineering and Technology (JIETY, vol. 2, no. 1, pp. 3026–6459, Mar. 2024, doi: 10.21831/jiety.v2i1.249.

[7] R. S. Nurhalizah, R. Ardianto, and P. Purwono, “Analisis Supervised dan Unsupervised Learning pada Machine Learning: Systematic Literature Review,” Jurnal Ilmu Komputer dan Informatika, vol. 4, no. 1, pp. 61–72, Aug. 2024, doi: 10.54082/jiki.168.

[8] V. Artanti, M. Faisal, and F. Kurniawan, “Klasifikasi Cardiovascular Diseases Menggunakan Algoritma K-Nearest Neighbors (KNN) Classification of Cardiovascular Diseases using K-Nearest Neighbors (KNN) Algorithm,” vol. 23, no. 2, pp. 467–479, May 2024, doi: 10.62411/tc.v23i2.10061.

[9] D. Fabiyanto and Z. Pratama Putra, “Validasi Efektivitas Logistic Regression untuk Diagnosa Penyakit Jantung melalui Pendekatan Machine Learning,” Jurnal Ilmiah FIFO, vol. 16, no. 2, p. 158, Nov. 2024, doi: 10.22441/fifo.2024.v16i2.006.

[10] E. Ramadanti, D. A. Dinathi, C. Sri, K. Aditya, and R. Chandranegara, “Diabetes Disease Detection Classification Using Light Gradient Boosting (LightGBM) With Hyperparameter Tuning,” Jurnal dan Penelitian Teknik Informatika, vol. 8, no. 2, 2024, doi: 10.33395/v8i2.13530.

[11] N. L. Sabili, R. Fajri, and M. Umbara, “Klasifikasi Penyakit Diabetes Menggunakan Algoritma Categorical Boosting Dengan Faktor Risiko Diabetes,” 2024.

[12] D. A. Hadi and D. A. N. Sirodj, “Metode Random Forest untuk Klasifikasi Penyakit Diabetes,” Bandung Conference Series: Statistics, vol. 3, no. 2, pp. 428–435, Aug. 2023, doi: 10.29313/bcss.v3i2.8354.

[13] B. Swarnadwip and S. Bose, “Random Forests: The Wisdom of Crowds in Action,” Journal of Emerging Trends in Computer Science and Applications (JETCSA), vol. 1, no. 1, pp. 67–91, Apr. 2025, doi: 10.65525/jetcsa.v1i1.5.

[14] A. Maulana, A. Pratama, D. Primanda, and N. Hariyanto, “Model Prediksi Kanker Paru-Paru dengan Random Forest Lung Cancer Prediction Model with Random Forest,” Jurnal Sisfotenika, vol. 15, no. 2, 2025, doi: 10.30700/sisfotenika.v15i1.569.

[15] Y. Chithra, P. Kiran, and M. P B, “The Novel Method for Data Preprocessing CLI,” Advances in Intelligent Systems and Technologies, pp. 117–120, Dec. 2022, doi: 10.53759/aist/978-9914-9946-1-2_21.

[16] T. Gori, A. Sunyoto, and H. Al Fatta, “Preprocessing Data dan Klasifikasi untuk Prediksi Kinerja Akademik Siswa,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 1, pp. 215–224, Feb. 2024, doi: 10.25126/jtiik.20241118074.

[17] T. A. E. Putri, T. Widiharih, and R. Santoso, “Penerapan Tuning Hyperparameter Randomsearchcv Pada Adaptive Boosting Untuk Prediksi Kelangsungan Hidup Pasien Gagal Jantung,” Jurnal Gaussian, vol. 11, no. 3, pp. 397–406, Jan. 2023, doi: 10.14710/j.gauss.11.3.397-406.