Lung cancer, logistic regression, prediction model
Abstract
Lung cancer is one of the most lethal forms of cancer and the primary cause of cancer-related mortality on a global scale. Given the rising incidence of lung cancer on an annual basis, it is of paramount importance to investigate further the potential risk factors associated with this disease in order to develop effective, personalized prevention strategies. In this study, a binary logistic regression model is used to predict the risk of lung cancer in patients by analyzing demographic and medical data. The dataset consisted of 300 study participants and 15 variables, such as smoking and gender. The dependent variable is whether the patient has lung cancer. In this study, smoking, peer pressure, chronic disease, fatigue, allergy, coughing, and swallowing difficulty have a significant positive effect on lung cancer. Furthermore, the overall predictive accuracy of the study model is 94.33%. Therefore, the predictive results of the logistic regression model are acceptable. In order to better predict lung cancer occurrence, more comprehensive clinical data and more advanced analysis techniques are needed, and more influencing factors need to be taken into account. The model lays the foundation for the prediction of lung cancer.
