Cancer is the main reason for a huge number of deaths worldwide, out of which lung cancer is the main cause of the highest mortality rates. Nearly 85% of males and 75% of females suffer from lung cancer. The cancer cells grow and keep multiplying which leads to the development of tumors. If these cells grow rapidly, it spreads to other parts of the body, this is known as Metastases. Identification of cancer at the final stage has very less chances of complete treatment and it might lead to the death of the patient. Therefore, early prediction before the final stage is highly essential to increase the survival rate. For early identification, various Machine learning techniques are used which will facilitate the fast treatment of the disease. The dataset consists of different attributes such as Smoking, Alcohol consumption, Chest pain, Shortness of Breath, etc. The various ML classifiers applied to the dataset are Decision tree, Logistic regression, SVM, Naive Bayes, KNN, and Random forest. The classification models are analyzed for different test and train ratios and the obtained Accuracy, Precision, Recall, Error rate, Specificity, F-Measure, and Time are noted. This process is carried out for both binary and multi-class classification. Multiclass classification considered here is 3 class classification, i.e. High, Low and Medium levels of lung cancer. The accuracy obtained tells up to what extent the classifier has correctly predicted the disease. The highest accurate model for both the classes obtained was SVM Classifier. The accuracy obtained was 100% with minimum execution time. Therefore, the SVM classifier using the Machine Learning technique can be applied to detect the presence of the disease and hence help the doctors in identifying it. By doing so, early diagnosis can be performed and required precautions can be taken.

Lung Cancer, SVM, Machine Learning, Metastases.