Analysis of Life Expectancy Rate Post Lung Surgery Using Machine Learning

It has become really important for patients to know the precise results that can happen post the treatment of lung cancer or that if they have any underlying health problem which can be the cause of death post lung cancer surgery. Doctors also need to know the full detailed report of patients’ health with the risk factors that can affect their survival rate for better treatment of their patients. As such results are crucial, we need to implement such techniques which can generate the most accurate results. For such accurate analysis, we use machine learning techniques to generate better results. Several machine learning and deep learning approaches are being used to estimate the survival rate of lung cancer patients post the surgery. Examination of various health factors is used for prediction, as health factors could be significant predictors. Seven machine learning techniques that are linear regression, XGBooster, random forests, Decision Tree, KNN, SVM, voting classifier and two deep learning techniques that are ANN and BILSTM are used for analyzing performance. Analysis of accuracy has been done using F1 score, precision, and recall as measuring factors. For the analysis of outcome prediction, we have taken accuracy.