A Comprehensive Survey of Machine Learning and Deep Learning Algorithms for Lung Cancer Prediction: A Comparative Analysis

Machine learning and deep learning have become important research tools for lung cancer prediction, classification, risk assessment, and prognosis. This survey reviewed major conventional machine learning algorithms, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, KNN, Naïve Bayes, Gradient Boosting, XGBoost, and AdaBoost, together with deep learning approaches such as ANN, CNN, RNN, and transfer learning. The reviewed literature demonstrates that algorithm performance is highly dependent on the characteristics of the underlying data and the specific clinical objective. Traditional machine learning and ensemble methods remain highly relevant for structured clinical and demographic datasets, while deep learning models, particularly CNNs, are well suited to complex medical imaging tasks. Recent systematic evidence suggests that AI-based models can achieve promising predictive discrimination, but performance differences across studies should be interpreted carefully because of variations in datasets, preprocessing procedures, prediction endpoints, and validation methods. The review also highlights several limitations that currently restrict the generalizability and clinical adoption of AI-based lung cancer prediction systems. These include dataset heterogeneity, limited sample sizes, class imbalance, overfitting, insufficient external validation, inconsistent evaluation practices, and inadequate reporting of experimental procedures. Future research should therefore move beyond the simple pursuit of higher accuracy. Greater emphasis should be placed on robust study design, diverse datasets, external and prospective validation, multimodal data integration, reproducible methodologies, and standardized benchmarking. The combination of rigorous machine learning methodology with clinically representative datasets can contribute to the development of more reliable lung cancer prediction systems. Overall, artificial intelligence offers substantial potential for supporting lung cancer risk assessment and prediction. However, successful translation from experimental research to clinical practice will depend on demonstrating that these models are not only accurate within research datasets but also robust, generalizable, reproducible, and clinically useful across diverse real-world populations.

[1] S. Leonard et al., “Comparing artificial intelligence and traditional regression models in lung cancer risk prediction: A systematic review and meta-analysis,” J. Amer. Coll. Radiol., 2025. [2] A. J. Didier, A. Nigro, Z. Noori, M. A. Omballi, S. M. Pappada, and D. M. Hamouda, “Application of machine learning for lung cancer survival prognostication—A systematic review and meta-analysis,” Front. Artif. Intell., vol. 7, 2024, Art. no. 1365777, doi: 10.3389/frai.2024.1365777. [3] “Performance of deep-learning solutions on lung nodule malignancy classification: A systematic review,” Frontiers in Oncology, 2023. [4] S. G. Armato III et al., “The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A completed reference database of lung nodules on CT scans,” Med. Phys., vol. 38, no. 2, pp. 915–931, 2011, doi: 10.1118/1.3528204. [5] 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, 2002, doi: 10.1613/jair.953. [6] L. Breiman, “Random forests,” Mach. Learn., vol. 45, pp. 5–32, 2001, doi: 10.1023/A:1010933404324. [7] C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, pp. 273–297, 1995, doi: 10.1007/BF00994018. [8] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2016, pp. 785–794, doi: 10.1145/2939672.2939785. [9] L. Breiman, J. Friedman, R. Olshen, and C. Stone, Classification and Regression Trees. Belmont, CA, USA: Wadsworth, 1984. [10] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY, USA: Springer, 2009.