Abstract—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.
Index Terms—Machine learning, lung and bronchus cancer,
survival prediction, performance evaluation.
The authors are with the Faculty of Engineering and Applied Science,
Department of Industrial Systems Engineering, University of Regina,
Canada (e-mail: Rouzbeh.Talebi@gmail.com, Rene.Mayorga@uregina.ca).
Cite: Rouzbeh Talebi Zarinkamar and Rene V. Mayorga, "Lifespan Prediction for Lung and Bronchus Cancer Patients via Machine Learning Techniques," International Journal of Machine Learning and Computing vol. 12, no. 5, pp. 245-251, 2022.
Copyright @ 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).