Drug Side-effects Prediction using Hierarchical Fuzzy Deep Learning for Diagnosing Specific Disease

Drug Side-effects Prediction using Hierarchical Fuzzy Deep Learning for Diagnosing Specific Disease

© 2022 by IJETT Journal
Volume-70 Issue-8
Year of Publication : 2022
Authors : Nithya B, Anitha G
DOI : 10.14445/22315381/IJETT-V70I8P214

How to Cite?

Nithya B, Anitha G, "Drug Side-effects Prediction using Hierarchical Fuzzy Deep Learning for Diagnosing Specific Disease," International Journal of Engineering Trends and Technology, vol. 70, no. 8, pp. 140-148, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I8P214

In drug discovery, the foremost challenging task is predicting drug-disease correlation using drugs' various indications and side effects on specific diseases for proper diagnosis. To combat this issue, Wasserstein Auto-Encoder with Convolutional Neural Network (WAE-CNN) model was developed, which uses the side effects constraints along with the drugs and patient attributes from the large-scale databases to predict drugs for specific diseases. But, the correlation variability between several drug-disease side effect categories is quite unfair. Few categories are more complex to predict than others. Therefore, this article presents a Hierarchical Fuzzy Deep CNN (HFDCNN)model to predict and recommend drugs for particular diseases considering side effects. First, the database is created by collecting data about patients, diseases, drugs and their side effects. Then, such data are fed to the HFDCNN for prediction. In the HFDCNN model, FDCNN is embedded into the attribute hierarchy. It segregates simple classes using a coarse classifier, whereas fine classifiers differentiate complex classes. In the learning phase, an element-wise pre-learning is supported by global fine-tuning with a multinomial logistic loss normalized by a coarse coherence factor. Also, conditional executions of fine classifiers and layer variable reduction make this HFDCNN more robust for many disease data associated with the drugs and their side effects. Finally, the test results exhibit that the HFDCNN model achieves 95.3%, 97.1% and 98.55% of accuracies in predicting the drugs for Chronic Kidney Disease (CKD), diabetes and heart diseases, correspondingly compared to the classical models.

Drug-disease correlation, Side effects, WAE-CNN, Attribute hierarchy, Fuzzy DCNN, Multinomial logistic loss, Conditional execution.

[1] Agatonovic- Kustrin S, & Morton D, “Data Mining in Drug Discovery and Design,” In Artificial Neural Network for Drug Design, Delivery and Disposition, Academic Press, pp. 181-193, 2016.
[2] Chittora, A., &Mekala A. M, “Discovery of Drug and Medicine Using Data Mining Techniques,” Research Journal of Pharmacy and Technology, vol. 10, no. 12, pp. 4147-4151, 2017.
[3] Yosipof, A., Guedes, R. C., & García-Sosa A. T, "Data Mining and Machine Learning Models for Predicting Drug Likeness and Their Disease or Organ Category,” Frontiers in Chemistry, vol. 6, pp. 1-11, 2018.
[4] Dunne, S., Shannon, B., Dunne, C., & Cullen W, “A Review of the Differences and Similarities Between Generic Drugs and their Originator Counterparts, Including Economic Benefits Associated with Usage of Generic Medicines, using Ireland as a Case Study,” BMC Pharmacology and Toxicology, vol. 14, no. 1, pp. 1-19, 2013.
[5] Tamargo, J., Le Heuzey, J. Y., & Mabo P, “Narrow Therapeutic Index Drugs: A Clinical Pharmacological Consideration to Flecainide,” European Journal of Clinical Pharmacology, vol. 71, no. 5, pp. 549-567, 2015.
[6] Jiménez, R., Anupol, J., Cajal, B., & Gervilla E, “Data Mining Techniques for Drug Use Research,” Addictive Behaviors Reports, vol. 8, no. 128-135, 2018.
[7] Bagherian, M., Sabeti, E., Wang, K., Sartor, M. A., Nikolovska-Coleska, Z., & Najarian K, “Machine Learning Approaches and Databases for Prediction of Drug–Target Interaction: A Survey Paper,” Briefings in Bioinformatics, vol. 22, no. 1, pp. 247-269, 2021.
[8] Nithya, B., & Anitha G, “Prediction of Drugs for Diseases with Side Effect and Patient Physical Attributes”.
[9] Nithya, B., & Anitha G, “The Optimal Time Slot Selection and Feature Selection for the Prediction of Drugs for Diseases,” International Journal of Nonlinear Analysis and Applications, vol. 12, pp. 2137-2151, 2021.
[10] Gandomi, A. H., & Alavi A. H, “Krill Herd: A New Bio-Inspired Optimization Algorithm,” Communications in Nonlinear Science and Numerical Simulation, vol. 17, no. 12, pp. 4831-4845, 2012.
[11] Mondal, A. K., Asnani, H., Singla, P., & Prathosh A. P, “FlexAE: Flexibly Learning Latent Priors for Wasserstein Auto-Encoders,” In Uncertainty in Artificial Intelligence, pp. 525-535, 2021.
[12] Yousefi-Azar, M., Varadharajan, V., Hamey, L., & Tupakula U, “Autoencoder-Based Feature Learning for Cyber Security Applications,” In IEEE International Joint Conference on Neural Networks, pp. 3854-3861, 2017.
[13] Hunta, S., Yooyativong, T., & Aunsri N, “A Novel Integrated Action Crossing Method for Drug-Drug Interaction Prediction in Non-Communicable Diseases,” Computer Methods and Programs in Biomedicine, vol. 163, pp. 183-193, 2018.
[14] Ibrahim, S. J. A., & Thangamani M, “Enhanced Singular Value Decomposition for Prediction of Drugs and Diseases with Hepatocellular Carcinoma Based on Multi-Source Bat Algorithm Based Random Walk,” Measurement, vol. 141, 176-183, 2019.
[15] HemanthSomasekar and Dr. KavyaNaveen, "A System For Identifying Synthetic Images Using Lstm: A Deep Learning Approach," International Journal of Computer Trends and Technology, vol. 69, no. 2, pp. 64-67, 2021. Crossref, https://doi.org/ 10.14445/22312803/IJCTT-V69I2P110
[16] Peng, J., Li, J., & Shang X, “A Learning-Based Method for Drug-Target Interaction Prediction Based on Feature Representation Learning and Deep Neural Network,” BMC Bioinformatics, vol. 21, no. 13, pp. 1-13, 2020.
[17] Yang, H., Ding, Y., Tang, J., & Guo F, “Drug–Disease Associations Prediction Via Multiple Kernel-Based Dual Graph Regularized Least Squares,” Applied Soft Computing, vol. 112, pp. 1-14, 2021.
[18] Jarada, T. N., Rokne, J. G., & Alhajj R, “SNF–CVAE: Computational Method to Predict Drug–Disease Interactions using Similarity Network Fusion and Collective Variational Autoencoder,” Knowledge-Based Systems, vol. 212, pp. 1-23, 2021.
[19] Ding, Y., Tang, J., & Guo F, “Identification of Drug-Target Interactions Via Multi-View Graph Regularized Link Propagation Model,” Neurocomputing, vol. 461, pp. 618-631, 2021.
[20] Jegou, H., Douze, M., & Schmid C, “Product Quantization for Nearest Neighbor Search,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 1, pp. 117-128, 2010.
[21] A.G.Hari Narayanan, Dr J Amar Pratap Singh, “Skin Disease Ensemble Classification using Transfer Learning and Voting Classifier,” International Journal of Engineering Trends and Technologies, vol. 12, pp. 287-293, 2021.
[22] Sunil Pandey,Naresh Kumar Nagwani,ShrishVerma, “Analysis and Design of High Performance Deep Learning Algorithms: Convolutional Neural Networks,” International Journal of Engineering Trends and Technologies, vol. 6, pp. 216-224, 2021.
[23] Khaled Mohamad Almustafa, “Prediction of Heart Disease and Classifiers’ Sensitivity Analysis,” BMC Bioinformatics, vol. 21, pp. 275, 2020.
[24] C K Gomathy, “The Prediction of Disease using Machine Learning,” International Journal of Scientific Research in Engineering and Management(IJSREM), vol. 5, no. 10, 2021.
[25] RayanAlanazi, “Identification and Prediction of Chronic Diseases using Machine Learning Approach,” Journal of Healthcare Engineering, vol. 2022, 2022
[26] Jiang, H. J., You, Z. H., & Huang Y. A, “Predicting Drug−Disease Associations Via Sigmoid Kernel-Based Convolutional Neural Networks, Journal of Translational Medicine, vol. 17, no. 1, pp. 1-11, 2019.