The study aimed to create a computer model for distinguishing large opacities in pneumoconiosis from lung cancer using CT image analysis. The research included 103 cases of pneumoconiosis and 85 cases of peripheral lung cancer, which were divided into a training set (132 patients) and a test set (56 patients). 108 features were extracted from the CT images, of which the eight most important ones were identified. Three machine learning algorithms were tested: logistic regression (LR), support vector machine (SVM) and AdaBoost. On the test set, the AdaBoost model achieved an accuracy of 86.0%, a sensitivity of 82.1%, and a specificity of 89.7%, with an AUC value of 0.900. The AdaBoost model showed better results than the LR and SVM models in both ensembles. The conclusion of the study states that the prediction model based on AdaBoost effectively differentiates large opacities of pneumoconiosis from peripheral lung cancer.