Progress in Development of Lung Cancer Survival Prediction Models Using Machine Learning Based on SEER Database

The SEER (Surveillance, Epidemiology, and End Results) database, a comprehensive public repository of clinical oncology data, has been increasingly used to construct clinical prediction models for predicting the prognosis of cancer. With the advances in machine learning, various algorithms including logistic regression (LR), support vector machines (SVM), decision trees (DT), random forest (RF), artificial neural networks (ANN), and extreme gradient boosting (XGBoost) have been successively employed in the development of lung cancer survival prediction models (LCSPMs). This study combs through the progress of these machine learning algorithms in constructing lung cancer survival prediction models, points out the problems of data imbalance, poor model interpretability, and lack of external validation, and clarifies the future development direction.