AI-Driven Predictive Modeling for Lung Cancer Detection and Management

Strategic Insights -

Researchers at AlMaarefa University have discussed new findings in personalized medicine, specifically focusing on the application of artificial intelligence (AI) in the detection and management of lung cancer. The study introduces an innovative method called CTGAN-RF, which uses conditional tabular generative adversarial networks (CTGAN) and random forest (RF) classifier to detect lung cancer through synthetic data generation. The proposed model demonstrated superior performance by achieving a 0.9893 score of accuracy and 0.99 value for precision, F1 score, and recall.

Key Takeaways:

  • The proposed CTGAN-RF method uses synthetic data generation to detect lung cancer, which outperformed traditional classifiers in dealing with class imbalance and improving prediction accuracy.
  • The implementation of different classifiers employed data balancing methods, including SMOTE and borderline-SMOTE, along with SMOTE ENN and unbalanced data configurations.
  • The extensive experimental evaluation included testing nine classification algorithms, and the proposed model consistently performed significantly better than traditional classifiers.
  • The study found that CTGAN-RF achieved a 0.9893 score of accuracy and 0.99 value for precision, F1 score, and recall.
  • The proposed methodology outperformed existing approaches for lung cancer diagnosis in terms of classification metrics.
  • The study provides an in-depth evaluation of synthetic data augmentation with machine learning in lung cancer detection, which has helped in the development of personalized treatment strategies in the fight against lung cancer.

Statistics:

  • The proposed CTGAN-RF method achieved a 0.9893 score of accuracy.
  • The model achieved a 0.99 value for precision, F1 score, and recall.
  • The study tested nine classification algorithms and found that CTGAN-RF consistently performed significantly better than traditional classifiers.
  • The implementation of different classifiers employed data balancing methods, including SMOTE and borderline-SMOTE (used in 4 cases), along with SMOTE ENN and unbalanced data configurations (used in 5 cases).

Sources:

  • AI-Driven Predictive Modeling for Lung Cancer Detection and Management Using Synthetic Data Augmentation and Random Forest Classifier. International Journal of Computational Intelligence Systems, 2025,18(1):1-20. (International Journal of Computational Intelligence Systems - https://www.atlantis-press.com/journals/ijcis).
  • NewsRx. Data on Personalized Medicine Discussed by Researchers at AlMaarefa University. Cancer Weekly. July 1, 2025; p 189.
  • https://doi-org.sdpl.idm.oclc.org/10.1007/s44196-025-00879-4 (free version of the journal article).
  • AlMaarefa University, Princess Nourah Bint Abdulrahman University Researchers Supporting Project.