Document Type : Research Article
Authors
1 Department of Computer engineering and information technology, Payame Noor University, Tehran, Iran.
2 Department of Statistics, Payame Noor University, Tehran, Iran.
10.30473/coam.2025.73974.1295
Abstract
Breast cancer is one of the most prevalent cancers among women and remains a leading cause of cancer-related mortality. Mammography is the primary imaging modality for the early detection of breast tumors. Providing timely and highly accurate diagnoses is a top priority for physicians and healthcare providers in the management of critical illnesses. This paper presents a Medical Decision Support System (MDSS) that utilizes Yager’s rule of combination to classify and diagnose breast cancer patients by integrating information from multiple data sources. Medical text reports (MTR) and key feature vectors extracted from electronic health records (EHR) were reduced using Principal Component Analysis (PCA) and then classified using Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), and Support Vector Machines (SVM). Medical images were preprocessed and classified using a U-Net model. A novel decision fusion algorithm, called weighted Yager, was introduced to determine the Breast Imaging-Reporting and Data System (BI-RADS) categories, taking into account the accuracy of each class in each classifier as evidence. The performance of the proposed system was evaluated based on standard metrics including accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score. The proposed system achieved the highest accuracy of 96.23\%, outperforming individual classifiers (CNN: 86.37%, MLP: 92.11%, SVM: 87.92%, U-Net: 92.97%, and Yager: 93.49%). The weighted Yager fusion method yielded the best performance with an accuracy of 96.23%, sensitivity of 98.80%, specificity of 85.90%, PPV of 86.21%, NPV of 97.82%, and F1-score of 85.87%. These findings demonstrate that integrating decisions from multiple classifiers significantly improves diagnostic accuracy and robustness.
Highlights
Highlights
- Developed a novel Medical Decision Support System (MDSS) framework utilizing Yager’s rule of combination to improve breast cancer diagnosis and classification accuracy.
- Integrated heterogeneous data sources, including Combined Medical Text Reports (MTR), Electronic Health Records (EHR), and medical imaging, to enhance decision-making robustness.
- Employed Principal Component Analysis (PCA) for effective feature extraction from textual and structured data, followed by classification using CNN, MLP, and SVM models.
- Applied U-Net architecture for preprocessing and accurate classification of medical images.
- Developed a weighted Yager decision fusion algorithm that dynamically assigns importance to classifiers based on their accuracy, enhancing BI-RADS categorization.
- Achieved state-of-the-art performance metrics, including accuracy, sensitivity, specificity, PPV, NPV, and F1-score, outperforming individual classifiers and traditional fusion methods.
- Demonstrated a maximum overall classification accuracy of 96.23%, surpassing individual classifiers (CNN, MLP, SVM, U-Net) and the original Yager approach.
- Confirmed that combining multiple classifier outputs significantly enhances the reliability and precision of breast cancer diagnostics in clinical decision support systems.
Keywords
Main Subjects
[1] Ahmed, S. (2023). “A software framework for predicting the maize yield using modified multilayer perceptron”, Sustainability, 15(4), 3017, doi: https://doi.org/10.3390/su15043017.
[2] Akram, M., Shahzadi, G. (2021). “A hybrid decision-making model under q-rung orthopair fuzzy Yager aggregation operators”, Granular Computing, 6(4), 763-777, doi: https://doi.org/10.1007/s41066-020-00229-z.
[3] Alesheykh, R. (2016). “Comparative analysis of machine learning algorithms with optimization purposes”, Control and Optimization in Applied Mathematics, 1(2), 63-75.
[4] Alhasani, A.T., Alkattan, H., Subhi, A.A., El-Kenawy, El.S.M., Eid, M.M. (2023). “A comparative analysis of methods for detecting and diagnosing breast cancer based on data mining”, Journal of Artificial Intelligence and Metaheuristics, 4(2), 08-17, doi: https://doi.org/10.54216/JAIM.040201.
[5] Balasubramaniam, S., Velmurugan, Y., Jaganathan, D., Dhanasekaran, S.J.D. (2023). “A modified LeNet CNN for breast cancer diagnosis in ultrasound images”, Diagnostics, 13(17), 2746, doi: https://doi.org/10.3390/diagnostics13172746.
[6] Batista, G.E., Prati, R.C., Monard, M.C. (2004). “A study of the behavior of several methods for balancing machine learning training data”, ACM SIGKDD Explorations Newsletter, 6(1), 20-29, doi: https://doi.org/10.1145/1007730.1007735.
[7] Boyer, B., Canale, S., Arfi-Rouche, J., Monzani, Q., Khaled, W., Balleyguier, C. (2013). “Variability and errors when applying the BIRADS mammography classification”, European Journal of Radiology, 82(3), 388-397, doi: https://doi.org/10.1016/j.ejrad.2012.02.005.
[8] Borkowski, K., Rossi, C., Ciritsis, A., Marcon, M., Hejduk, P., Stieb, S., Boss, A., Berger, N. (2020). “Fully automatic classification of breast MRI background parenchymal enhancement using a transfer learning approach”, Medicine, 99(29): p e21243, doi: https://doi.org/10.1097/MD.0000000000021243.
[9] Boroumandzadeh, M., Parvinnia, E., Boostani, R., Sefidbakht, S. (2021). “A decision support system framework based on text mining and decision fusion techniques to classify breast cancer patients”, Control and Optimization in Applied Mathematics, 6(1), 11-29, doi: https://doi.org/10.30473/coam.2021.60533.1175.
[10] Boumaraf, S., Liu, X., Ferkous, C., Ma, X. (2020). “A new computer-aided diagnosis system with modified genetic feature selection for BI-RADS classification of breast masses in mammograms”, BioMed Research International, 2020, doi: https://doi.org/10.1155/2020/7695207.
[11] Bozkurt, S., Gimenez, F., Burnside, E.S., Gulkesen, K.H., Rubin, D.L. (2016). “Using automatically extracted information from mammography reports for decision-support”, Journal of Biomedical Informatics, 62, 224-231, doi: https://doi.org/10.1016/j.jbi.2016.07.001.
[12] Carlsson, C., Brunelli, M., Mezei, J. (2012). “Decision making with a fuzzy ontology”, Soft Computing, 16, 1143-1152, doi: https://doi.org/10.1007/s00500-011-0789-x.
[13] Castro, S.M., Tseytlin, E., Medvedeva, O., Mitchell, K., Visweswaran, Sh., Bekhuis, T., Jacobson, R.S. (2017). “Automated annotation and classification of BI-RADS assessment from radiology reports”, Journal of Biomedical Informatics, 69, 177-187, doi: https://doi.org/10.1016/j.jbi.2017.04.011.
[14] Chang, C.-C., Lin, C.-J. (2011). “LIBSVM: A library for support vector machines”, ACM Transactions on Interactive Intelligent Systems, 2(3), 27, doi: https://doi.org/10.1145/1961189.1961199.
[15] Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P. (2002). “Smote: Synthetic minority over-sampling technique”, Journal of Artificial Intelligence Research, 16, 321-357, doi: https://doi.org/10.1613/jair.953.
[16] Cochran, W.G. (1977). “Sampling techniques”, 3rd Edition, John Wiley & Sons, New York.
[17] Destrempes, F., Trop, I., Allard, L., Chayer, B., Garcia-Duitama, J., El Khoury, M., Lalonde, L., Cloutier, G. (2020). “Added value of quantitative ultrasound and machine learning in BI-RADS 4–5 assessment of solid breast lesions”, Ultrasound in Medicine & Biology, 46(2), 436-444, doi: https://doi.org/10.1016/j.ultrasmedbio.2019.10.024.
[18] Esmaeili, M., Ayyoubzadeh, S.M., Ahmadinejad, N., Ghazisaeedi, M., Nahvijou, A., Maghooli, K. (2020). “A decision support system for mammography reports interpretation”, Health Information Science and Systems, 8(1), 17, doi: https://doi.org/10.1007/s13755-020-00109-5.
[19] Fogliatto, F.S., Anzanello, M.J., Soares, F., Brust-Renck, P.G. (2019). “Decision support for breast cancer detection: Classification improvement through feature selection”, Cancer Control, 26(1), doi: https://doi.org/10.1177/1073274819876598.
[20] Gao, H., Aiello Bowles, E.J., Carrell, D., Buist, D.S.M. (2015). “Using natural language processing to extract mammographic findings”, Journal of Biomedical Informatics, 54, 77-84, doi: https://doi.org/10.1016/j.jbi.2015.01.010.
[21] Ghazalnaz Sharifonnasabi, F., Makhdoom, I. (2022). “Comparison of deep learning and machine learning algorithms to diagnose and predict breast cancer”, In: Ullah, A., Anwar, S., Calandra, D., Di Fuccio, R. (eds) Proceedings of International Conference on Information Technology and Applications, ICITA, Lecture Notes in Networks and Systems, 839. Springer, Singapore, doi: https://doi.org/10.1007/978-981-99-8324-7_4.
[22] Gupta, A., Banerjee, I., Rubin, D.L. (2018). “Automatic information extraction from unstructured mammography reports using distributed semantics”, Journal of Biomedical Informatics, 78, 78-86, doi: https://doi.org/10.1016/j.jbi.2017.12.016.
[23] Hossaina, Sh., Azamb, S., Montahac, S., Karimb, A., Sultana Chowaa, S., Mondola, Ch., Hasana, Md.Z., Jonkman, M. (2023). “Automated breast tumor ultrasound image segmentation with hybrid UNet and classification using fine-tuned CNN model”, Heliyon, 9(11), e21369, doi: https://doi.org/10.1016/j.heliyon.2023.e21369.
[24] Jais, I.K.M., Ismail, A.R., Nisa, S.Q. (2019). “Adam optimization algorithm for wide and deep neural network”, Knowledge Engineering and Data Science, 2(1), 41-46, doi: https://doi.org/10.17977/um018v2i12019p41-46.
[25] Japkowicz, N., Stephen, S. (2002). “The class imbalance problem: A systematic study”, Intelligent Data Analysis, 6(5), 429-449, doi: https://doi.org/10.3233/IDA-2002-6504.
[26] Jesneck, J.L., Nolte, L.W., Baker, J.A., Floyd, C.E., Lo, J.Y. (2006). “Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis”, Medical Physics, 33(8), 2945-2954, doi: https://doi.org/10.1118/1.2208934.
[27] Jia, W., Sun, M., Lian, J., Hou, S. (2022). “Feature dimensionality reduction: a review”, Complex & Intelligent Systems, 8(3), 2663-2693, doi: https://doi.org/10.1007/s40747-021-00637-x.
[28] Li, B., Drozd, A., Guo, Y., Liu, T., Matsuoka, S., Du, X. (2019). “Scaling Word2Vec on big corpus”, Data Science and Engineering, 4(2), 157-175, doi: https://doi.org/10.1007/s41019-019-0096-6.
[29] Long, J., Shelhamer, E., Darrell, T. (2015). “Fully convolutional networks for semantic segmentation”, in: 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA. 3431-3440, doi: https://doi.org/10.1109/CVPR.2015.7298965.
[30] Manalı, D., Demirel, H., Eleyan, A. (2024). “Deep learning based breast cancer detection using decision fusion”, Computers, 13(11), 294, doi: https://doi.org/10.3390/computers13110294.
[31] Nal Kalchbrenner, E.G., Blunsom, Ph. (2014). “A convolutional neural network for modelling sentences”, arXiv, doi: https://doi.org/10.48550/arXiv.1404.2188.
[32] Oh, S., Lee, M.S., Zhang, B.T. (2011). “Ensemble learning with active example selection for imbalanced biomedical data classification”, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 8(2), 316-325, doi: https://doi.org/10.1109/TCBB.2010.96.
[33] Patro, S.G.K., Kumar Sahu, K. (2015). “Normalization: A preprocessing stage”, arXiv, abs/1503.06462, doi: https://doi.org/10.48550/arXiv.1503.06462.
[34] Percha, B., Nassif, H., Lipson, J., Burnside, E., Rubin, D. (2012). “Automatic classification of mammography reports by BI-RADS breast tissue composition class”, Journal of the American Medical Informatics Association, 19(5), 913-916, doi: https://doi.org/10.1136/amiajnl-2011-000607.
[35] Punn, N.S., Agarwal, S. (2022). “Modality specific U-Net variants for biomedical image segmentation: A survey”, Artificial Intelligence Review, 55(7), 5845-5889, doi: https://doi.org/10.1007/s10462-022-10152-1.
[36] Ronneberger, O., Fischer, P., Brox, T. (2015). “U-Net: Convolutional networks for biomedical image segmentation”, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Cham, 234-241, Springer International Publishing, doi: https://doi.org/10.1007/978-3-319-24574-4_28.
[37] Sefidbakht, S., Jalli, R., Izadpanah, E. (2015). “Adherence of academic radiologists in a non-English speaking imaging center to the BI-RADS standards of reporting breast MRI”, Journal of Clinical Imaging Science, 5, 66, doi: https://doi.org/10.4103/2156-7514.172970.
[38] Siegel, R.L., Miller, K.D., Wagle, N.S., Jemal, A.J.C.C.J.C. (2023). “Cancer Statistics”, CA: A Cancer Journal for Clinicians, 73(1), 17-48, doi: https://doi.org/10.3322/caac.21763.
[39] Sippo, D.A., Warden, G.I., Andriole, K.P., Lacson, R., Ikuta, I., Birdwell, R.L., Khorasani, R. (2013). “Automated extraction of BI-RADS final assessment categories from radiology reports with natural language processing”, Journal of Digital Imaging, 26(5), 989-94, doi: https://doi.org/10.1007/s10278-013-9616-5.
[40] Tang, F., Adam, L., Si, B. (2018). “Group feature selection with multiclass support vector machine”, Neurocomputing, 317, 42-49, doi: https://doi.org/10.1016/j.neucom.2018.07.012.
[41] Xu, Q., Zhang, M., Gu, Z., Pan, G. (2019). “Overfitting remedy by sparsifying regularization on fully-connected layers of CNNs”, Neurocomputing, 328, 69-74, doi: https://doi.org/10.1016/j.neucom.2018.03.080.
[42] Yager, R.R. (1988). “On ordered weighted averaging aggregation operators in multicriteria decisionmaking”, IEEE Transactions on Systems, Man, and Cybernetics, 18(1), 183-190, doi: https://doi.org/10.1109/21.87068.
[43] Yan, R., Zhang, F., Rao, X., Lv, Zh., Li, J., Zhang, L., Liang, Sh., Li, Y., Ren, F., Zheng Ch., Liang, J. (2021). “Richer fusion network for breast cancer classification based on multimodal data”, BMC Medical Informatics and Decision Making, 21c, 1-15, doi: https://doi.org/10.1186/s12911-020-01340-6.
[44] Zahaby, M., Makhdoom, I. (2025). “Enhanced decision support system for breast cancer diagnosis with weighted ensemble learning methods”, Journal of Data Science and Modeling, 71-102, doi: https://doi.org/10.22054/jdsm.2025.82414.1055.
[45] Zahaby, M., Shiri, M.E., Haj Seyed Javadi, H., Broumandzadeh, M. (2024). “Automatic classification of BI-RADS in mammography reports using data fusion”, Armaghane Danesh, 29(3), 365-85, doi: http://dx.doi.org/10.61186/armaghanj.29.3.365.
[46] Zahaby, M., Shiri, M.E., Haj Seyed Javadi, H., Boroumandzadeh, M. (2025). “Decision support system for improving breast cancer diagnosis using ensemble learning”, Computing and Informatics, 44(1), 124-150, doi: https://doi.org/10.31577/cai_2025_1_124.
[47] Zhang, X. et al. (2019). “Extracting comprehensive clinical information for breast cancer using deep learning methods”, International Journal of Medical Informatics, 132, 103985, doi: https://doi.org/10.1016/j.ijmedinf.2019.103985.
)