Lung Cancer Prediction based on KNN, Logistic Regression, and Random Forest Algorithm

Abstract

Cancer has become the biggest killer of human health in the 21st century, among them, lung cancer is the "number one killer" of cancer ", and has become the disease with the highest incidence rate of cancer. However, many factors cause lung cancer. Therefore, to effectively control cancer and reduce the incidence rate of lung cancer, it is very important to predict the incidence of lung cancer caused by different factors. By calling the dataset in Kaggle, we can visualize and preprocess data from 25 factors that may cause lung cancer incidence, and use the machine of K-nearness model, random forest model and logical regression model Learn the model for prediction and obtain the model with the highest accuracy. It was found that the random forest algorithm performed the best among the three models used, so the random forest algorithm was used for model tuning, adjusting parameters to improve accuracy. Finally, the model accuracy was increased from 0.96 to 0.98, achieving the expected effect. This study is beneficial for a clearer and more accurate understanding of the impact of different factors on the incidence of lung cancer, as well as for more efficient prediction of lung cancer in the medical field.