Search

Introduction: Prostate cancer is one of the leading causes of death in men, and the early detection of this disease can be a significant factor in controlling and managing it. Applying data mining techniques can lead to the extraction of hidden knowledge from a huge amount of data and can help diagnose this disease by physicians. This study aims to determine the algorithm with the best performance to diagnose prostate cancer. Material and Methods: In this study, nine data mining techniques, including Support Vector Machine, Decision Tree, Naive Bayes, K-Nearest Neighbors, Neural Network, Random Forest, Deep Learning, Auto-MLP, and Rule Induction algorithms, were used to extract hidden patterns from prostate cancer data. In this study, the data of 100 patients, which included eight characteristics, were used, and the RapidMiner Studio environment was employed for modeling. To compare the performance of the mentioned approaches used in this study to diagnose prostate cancer, accuracy, recall, precision, AUC, sensitivity, and specificity were calculated and reported for all techniques. Results: The results of this study showed that the accuracy of the applied algorithms was between 77% and 84%. Using different criteria to evaluate the techniques used showed that the two algorithms K-Nearest Neighbors and Neural Network, had better performance and accuracy (84%) than other methods. The sensitivity in these two algorithms was 80% for Neural Networks and 85% for K-Nearest Neighbors, respectively. Conclusion: The usage of different data mining techniques can lead to the discovery of hidden patterns among an enormous amount of data related to prostate cancer, and as a result, it leads to the early diagnosis of this disease and saves the subsequent costs. [ABSTRACT FROM AUTHOR]

Background: Artificial intelligence has recently shown remarkable success in analyzing medical images due to the rapid expansion of deep learning algorithms. Objective: Researchers in this study aimed to provide accurate diagnosis and classification of acute lymphoblastic leukemia by processing microscopic. This diagnosis approach is based on deep learning, which is the core of the clinical decision system. Material and Methods: A large number of pathological images related to acute lymphoblastic leukemia and healthy cells are chosen. The dataset CodaLab competition included 12,528 images of 4,037 healthy cells and 8,491 leukemic cells. Extracted critical features were used to classify acute lymphoblastic leukemia and healthy cells by a pre-trained network, i.e., VGG 16. From the total number of images, 80% (10022 numbers) were used as training data and 20% (2506 numbers) as test data. The activation for all layers except the last layer was the ReLU function. Adam was selected for the optimization function with a learning rate of 0.0001. The intelligent diagnostic system was created using the Java programming language. Results: The training accuracy of the VGG-16 is 97.41%, and the validation accuracy is 84.62%. Precision, recall, and F-measure related to leukemia class are 0.88, 0.91, and 0.90, respectively. VGG-16 was used as the processing core in the decision support system. Conclusion: This system in medical centers is helpful for purposes such as timely diagnosis, reducing patient hospital stay and treatment costs, and improving the patient referral system. [ABSTRACT FROM AUTHOR]