A Methodology to Predict the Lung Cancer and its Adverse Effects on Patients from an Advanced Correlation Analysis Method

Abstract

Using symptoms as a basis for diagnosing lung cancer. Lung cancer detection is accomplished by using different machine learning techniques and regression algorithms. By comparing the efficacy of different regression algorithms for predicting lung cancer, various factors including age, gender, chest discomfort, shortness of breath, alcohol intake, chronic illness, trouble swallowing, anxiety, and peer pressure are taken into consideration. Lung cancer prediction and evaluation are accomplished by using different regression methods such as linear algorithm, polynomial regression, logistic regression, logarithmic regression and multiple regression. With a predictive accuracy of 96%, multiple regression remains superior to other regression techniques when it comes to lung cancer prediction. The R-squared value can be calculated by using a number of regression approaches, which may also be used to evaluate the association between various symptoms and lung cancer. Lung cancer is diagnosed by using the R squared value, which is calculated by using several algorithms and considers symptoms including chronic illness.