The Early Stage Lung Cancer Prognosis Prediction Model based on Support Vector Machine

According to the annual statistics of the American Cancer Society, lung cancer has become the leading cause of death for cancer patients. It is therefore vital to research lung cancer prognosis prediction model. From the characteristics of cancer data samples, we consider the unbalanced category data. Due to the small number of samples, one of the commonly used over-sampling techniques is selected, which is an improved Synthetic Minority Over-sampling Technique (Borderline-SMOTE) to expand a few types of samples. For labeling the dataset by 5-year survival time, support vector machines (SVM) and Cox-proportional hazard regression model (COX) were used for training and calculating, respectively. The results show that the performance of the proposed prognosis model based on SVM is better. Similarly, 2-year survival time as the standard for labeling the dataset, the experimental results also show that the performance of the proposed model is better, which verifies the validity and reliability of the designed model.