A Comparative Analysis of Lung Cancer Prediction Using Machine Learning Techniques

Smoking is the primary cause of lung cancer in India, and men are more likely than women to smoke. Lung cancer is far more likely to occur in India, where solid fuel cooking produces significant indoor air pollution. Historical data and predictive modeling can be used to make precise predictions for issues like the potential for customer attrition, possible fraud, illness prognosis, customer churn, and more. The paper below explores machine learning techniques for predicting lung cancer. SVM, XGBoost, gradient boosting classifier, decision tree classifier, random forest classifier, logistic regression, and KNN are the methods that we have implemented. Observationally, random forest classifier and XGBoost are the most accurate classifiers. The following attributes affect the prediction: gender, age, smoking, finger yellowing, anxiety, peer pressure, chronic disease, exhaustion, allergy, wheezing, alcohol use, chest discomfort, swallowing issues, breathlessness, and lung cancer. In this research, seven machine learning algorithms were used: logistic regression (91.66%), decision tree classifier (95.37%), random forest classifier (99.07%), gradient boosting classifier (94.44%), SVM (95.37%), XGBoost (99.00%), and KNN (93.51%).