Prediction of Survival Rate from Non-Small Cell Lung Cancer using Improved Random Forest
Pranamita Nanda, N. Duraipandian · 2020
The major advantage of survival rate prediction is to help patients by giving a better understanding about the success rate of his treatment. In case of lung cancer it is difficult to determine which feature should be used in order to determine this information. In this paper a number of algorithms are applied to the data set to classify the survival rate of Non -Small Cell lung cancer patients along with our proposed method Improved Random forest. The key data features used in these algorithms are overall treatment time, stages, total tumor dose, gender and age. The predictive power of various algorithms are compared. The results show that among the four individual models developed, Improved Random Forest is the most accurate one with an accuracy of 98%. Hence this work provides an effective and powerful approach to predict survival rate of NSCLC patients.