A Comparative Study of Lung Cancer Detection using Machine Learning Algorithms

A Comparative Study of Lung Cancer Detection using Machine Learning Algorithms

Abstract: The diagnosis and detection of lung cancer has been conducted using various methods of data analysis and classification. Because lung carcinoma has no known cause, circumvention becomes impossible, making early detection of tumors in lungs the best way to treat lung cancer. It is called lung cancer when cancerous cells grow in lungs.

Increasing cancer rates have resulted in a higher mortality rate for both men and women. It is impossible to prevent lung cancer, but its risk can be reduced. In order to improve the survival rate of lung cancer patients, it is crucial to detect it at the earliest stage. There is a direct relationship between the number of chain smokers and lung cancer patients. There have been several attempts to develop predictive models to guide clinicians in the management of indeterminate lung nodules discovered incidentally or during screening. The use of such systems could lead to less variability in nodule classification, better decision making, and a reduction in the number of benign nodules that are not needed to be followed up. The lung cancer prediction was analysed using classification algorithms such as Naive Bayes, SVM, Decision tree and Logistic Regression. The key objective of this paper is the early diagnosis of lung cancer by examining the performance of classification algorithms.

Keywords— DecisionTree;LogisticRegression;LungCancer Prediction,;NaïveBayes;Support Vector Machine