Statistical analysis and risk prediction of lung cancer exploiting logistic regression

Abstract

Cancer is a disease with a high mortality rate. Early prediction of cancer is an important means to completely cure the disease. Therefore, there is an ever-increasing demand for technologies to detect early cancer nodules. As an easily misdiagnosed disease, the mortality rate of lung cancer has reached the highest level in recent years. Early diagnosis of lung cancer can save many lives. The study used logistic regression to predict cancer risk by collecting and analyzing patient data. Logistic regression, referred to as logistic regression analysis, is a general linear regression analysis model that relates to supervised learning in machine learning. First, n sets of data are given to the model as a training set for training, and then the model could be leveraged to classify other data (test sets), and finally the classification results could be achieved. P indicators make up each batch of data. This study used a dataset from Kaggle, which contains information from one thousand patients with lung cancer, and it has 23 eigenvalues. This dataset classifies the predicted values as high, medium, and low. The regression results show that the precision value of the low prediction value is 84%, the precision value of the middle prediction value is 88%, and the precision value of the low prediction value is 93%. The result is that as the number of samples with different predicted values increases, the precision values increase.