Volume 12, Issue 3 (Iranian Quarterly Journal of Breast Disease 2019)                   ijbd 2019, 12(3): 26-35 | Back to browse issues page


XML Persian Abstract Print


1- Ph.D. Student in Analytical Chemistry, Department of Chemistry, Lorestan University, Khorramabad, Iran
2- Department of Chemistry, Faculty of Basic Science, Lorestan University, Khorramabad, Iran , alizadehkam@yahoo.com
Abstract:   (4311 Views)
Introduction: Breast cancer is the most prevalent cause of cancer mortality among women. Early diagnosis of breast cancer gives patients greater survival time. The present study aims to provide an algorithm for more accurate prediction and more effective decision-making in the treatment of patients with breast cancer.
Methods: The present study was applied, descriptive-analytical, based on the use of computerized methods. We obtained 699 independent records containing nine clinical variables from the UCI machine learning. The EM algorithm was used to analyze the data before normalizing them. Following that, a combination of neural network model based on multilayer perceptron structure with the Whale Optimization Algorithm (WOA) was used to predict the breast tumor malignancy.
Results: After preprocessing the disease data set and reducing data dimensions, the accuracy of the proposed algorithm for training and testing data was 99.6% and 99%, respectively. The prediction accuracy of the proposed model was 99.4%, which would be a satisfying result compared to different methods of machine learning in other studies.
Conclusion: Considering the importance of early diagnosis of breast cancer, the results of this study may have highly useful implications for health care providers and planners so as to achieve the early diagnosis of the disease.
Full-Text [PDF 722 kb]   (2477 Downloads)    
Conclusion: Considering the importance of early diagnosis of breast cancer, the results of this study may have highly useful implications for health care providers and planners so as to achieve the early diagnosis of the disease.

Type of Study: Research | Subject: Breast Diseases
Received: 2019/05/15 | Accepted: 2019/08/14 | Published: 2019/11/13

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.