EARLY DETECTION OF LUNG CANCER USING PREDICTIVE MODELING INCORPORAT IN GC TG AN FEATURES AND TREE-BASED LEARNING
DOI:
https://doi.org/10.5281/zenodo.21374616Keywords:
Lung Cancer, Accuracy, Predictive Model, Data Models, Biological System Modeling, Medical Diagnostic Imaging, Support Vector Machines, Analytical Models, Prediction Algorithms, Nearest Neighbor MethodsAbstract
Lung cancer remains a deadly tumor globally, and accurate and early diagnostic methods are needed to improve the survival rate. The integration of artificial intelligence techniques with predictive modeling offers efficient techniques for the extraction of complex medical data and the support of decision-making in healthcare. The data used was obtained from Kaggle, and includes a plethora of lung cancer features extracted from patients' medical data. The dataset comprises medically relevant attributes for classification. A feature selection approach involving Chi² and MI was used to identify significant predictors, thereby supplying an effective feature set for the classification models in high-dimensional data. The classification was performed using several ML algorithmswith5-foldcross-validation -GBC, RF, ETC, SVM, KNN, LR, DT, SGDC, NB, and XGB. Various class balancing techniques, such as SMOTE, Borderline SMOTE, SMOTE-ENN and CTGAN, were applied to reduce class imbalance, thereby significantly improving model performance. To enhance accuracy, the data was preprocessed by removing outliers and using advanced resampling techniques (ADASYN+ Cluster Centroids) in over-under sampling, and GBC achieved the highest accuracy of 99.05%. Finally, to improve model interpretability, the explainable AI interpretability methods LIME and SHAP were applied, and a Flask-based application was developed to allow user input for real-time prediction.
References
I. Ansari, M. M., Kumar, S., Chola, C., Heyat, M. B. B., Akhtar, F., Hayat, M. A. B., & Pomary, D. (2025). A Novel Machine and Deep Learning–Based Ensemble Techniques for Automatic Lung Cancer Detection. BioMed Research International, 2025(1), 6666688.
II. Patil, K., Dholakiya, N., Padhiyar, D., Anjaria, B., &Rana, K. (2025). A Hybrid Explainable AI Framework for Early Lung Cancer Detection Using CTGAN-Augmented Clinical Data, Gene Biomarkers, and Transformer-CNN Networks. Metallurgical and Materials Engineering, 31(4), 373-379.
III. Pavithran, M. S., & Saranyaraj, D. (2025). Lung cancer risk prediction using augmented machine learning pipelines with explainable AI. Frontiers in Artificial Intelligence, 8, 1602775.
IV. Pavithran, M. S., & Saranyaraj, D. (2025). Lung cancer risk prediction using augmented machine learning pipelines with explainable AI. Frontiers in Artificial Intelligence, 8, 1602775.
V. Ramkumar, M. O., Monica, R., Jaya Kumar, D., Rajmohan, R., & Arul Selvam, V. (2025, June). Lung Cancer Detectionusing3DU-NetBased DENSENET with Multimodal Images CT scans and his to pathological Images. In 2025 International Conference on Emerging Technologies in Engineering Applications (ICETEA)(pp.1-6). IEEE.
VI. R. Javed, T. Abbas, A. H. Khan, A. Daud, A. Bukhari, and R. Alharbey, “Deep learning for lungs cancer detection: A review,” Artif. Intell. Rev., vol. 57, no. 8, p. 197, Jul. 2024.
VII. M. Shafiquzzaman Bhuiyan, I. Kabir Chowdhury, M. Haider, A. Hossain Jisan, R. Mahmud Jewel, R. Shahid, and M. Zannatun Ferdus, “Advancements in early detection of lung cancer in public health: A comprehensive study utilizing machine learning algorithms and predictive models,” J. Comput. Sci. Technol. Stud., vol. 6, no. 1, pp.113–121, Jan. 2024.
VIII. S. M. Nabeel, S. U. Bazai, N. Alasbali, Y. Liu, M. I. Ghafoor, R. Khan, C. S. Ku, J. Yang, S. Shahab, and L. Y. Por, “Optimizing lung cancer classification through hyperparameter tuning,” Digit. Health, vol. 10, Jan. 2024, Art. no. 20552076241249661.
IX. F. Mercaldo, M. G. Tibaldi, L. Lombardi, L. Brunese, A. Santone, and M. Cesarelli, “An explainable method for lung cancer detection and localisation from tissue images through convolutional neural networks,” Electronics, vol. 13, no. 7, p. 1393, Apr. 2024.
X. Hugging Face Datasets. (2024). Lung Cancer Dataset. Accessed: May16, 2024. [Online]. Available: https://huggingface.co/datasets/nateraw/lungcancer
XI. M. Dirik, “Machine learning-based lung cancer diagnosis,” Turkish J. Eng., vol. 7, no. 4, pp. 322–330, Oct. 2023.
XII. K. Mohan and B. Thayyil, “Machine learning techniques for lung cancer risk prediction using text dataset,” Int. J. Data In format. Intell. Comput., vol. 2, no. 3, pp. 47–56, Sep. 2023.
XIII. F. M. Fatoki, E. K. Akinyemi, and S. A. Phlips, “Prediction of lungs cancer diseases datasets using machine learning algorithms,” Current J. Appl. Sci. Technol., vol. 42, no. 11, pp. 15–23, May 2023.
XIV. S. Tomassini, N. Falcionelli, P. Sernani, L. Burattini, and A. F. Dragoni, “Lung nodule diagnosis and cancer histology classification from computed tomography data by convolutional neural networks: A survey,” Comput. Biol. Med., vol. 146, Jul. 2022, Art. no. 105691.
XV. E. Dritsas and M. Trigka, “Lung cancer risk prediction with machine learning models,” Big Data Cognit. Comput., vol. 6, no. 4, p. 139, Nov.2022.
XVI. C. A. Kumar, S. Harish, P. Ravi, M. Svn, B. P. Kumar, V. Mohanavel, and A. K. Asfaw, “Lung cancer prediction from text datasets using machine learning,” BioMed Res. Int., vol. 2022, no. 1, 2022, Art. no.6254177.
XVII. V. Vasudha Rani, S. Das, and T. K. Kundu, “Risk prediction model for lung cancer disease using machine learning techniques,” in Innovations in Computer Science and Engineering. Singapore: Springer, 2022, pp.417–425.
XVIII. Y. Gültepe, “Performance of lung cancer prediction methods using different classification algorithms,” Comput., Mater. Continua, vol.67, no. 2, pp. 2015–2028, 2021.
XIX. M. Guo, F. Wu, G. Hu, L. Chen, J. Xu, P. Xu, X. Wang, Y. Li, S. Liu,
S. Zhang, and Q. Huang, “Autologous tumor cell–derivedmicroparticlebasedtargetedchemotherapyinlungcancerpatientswithmalignant pleural effusion,” Sci. Transl. Med., vol. 11, no. 474, Jan.2019, Art. no. eaat5690.
XX. N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” J. Artif. Intell. Res., vol. 16, pp. 321–357, Jun. 2002.
XXI. A. Fernandez, S. Garcia, F. Herrera, and N. V. Chawla, “SMOTE for learning from imbalanced data: Progress and challenges, marking the15-year anniversary,” J. Artif. Intell. Res., vol. 61, pp. 863–905, Apr.2018.
XXII. W. Li, J. Chen, J. Cao, C. Ma, J. Wang, X. Cui, and P. Chen, “EID-GAN: Generative adversarial nets for extremely imbalanced data augmentation,” IEEE Trans. Ind. In format., vol. 19, no. 3, pp. 3208–3218, Mar. 2023.
XXIII. H. Han, W.-Y. Wang, and B.-H. Mao, Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning. Berlin, Germany: Springer, 2005.
XXIV. L. Xu, M. Skoularidou, A. Cuesta-Infante, and K. Veeramachaneni, “Modeling tabular data using conditional GAN,” in Proc. Adv. NeuralInf. Process. Syst., vol. 32, 2019, pp. 7335–7345.
XXV. D. Unzueta. (2021). How to Generate Tabular Data Using CTGANS. Towards Data Science. Accessed: 31stJan.2025.[Online].Available:https://towardsdatascience.com/how-to-generate-tabular-data-using-ctgans-d91a56054955
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Educational Journal of Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
