Lifespan Prediction for Lung and Bronchus Cancer Patients via Machine Learning Techniques

Patients' accurate survival predictions can influence treatment planning and costs, particularly lung cancer, which is one of the leading causes of cancer-related death.Machine Learning (ML) techniques are powerful in increasing the accuracy of such predictions.However, only a few studies have used an ML approach for actual lifespan prediction for cancer patients using the Surveillance, Epidemiology, and End Results (SEER) program database.This study intends to apply several well-known ML models, namely, a developed Deep Neural Networks (DNN), Linear Regression, Support Vector Machine (SVM), Gradient Boosting Machine (GBM), Random Forest (RF), and Adaboost, to predict the actual survival time on a monthly basis for lung cancer patients.The results indicate that the models give better performance for low to average survival times (0 to 25 months) that make up the majority of the data.The best model was the developed DNN with a Root Mean Square Error (RMSE) value of 12.672.In contrast, the Adaboost model was the worst-performing technique since it had weak discrete power for the data.