Detection of Lung Cancer using Machine Learning Techniques Based on Routine Blood Indices
Puneet Puneet, Anamika Chauhan
Abstract
Cancer occurs due to the development of a large number of abnormal cells that causes uncontrolled growth and division of abnormal cells. The purpose of this research is to predict lung cancer using machine learning techniques based on routine blood indices and have better predictive results. We have used machine learning techniques such as XGBoost, Logistic Regression, SVM, Gaussian Naive Bayes, Decision Tree and KNN with GridSearchCV. Various scikit-learn algorithms have been used for feature selection, and only those features are selected that are important for our model. We found that XGBoost using GridSearchCV classification model is most suited for this work.
Topics & Concepts
Decision treeMachine learningNaive Bayes classifierArtificial intelligenceComputer scienceFeature selectionSupport vector machineLogistic regressionLung cancerOncologyMedicineRadiomics and Machine Learning in Medical ImagingArtificial Intelligence in HealthcareLung Cancer Diagnosis and Treatment