Early Detection and Classification of Biomedical Atherosclerosis using Feature Subset Selection with Optimal Deep Learning Model
Keywords:
Atherosclerosis, Medical Decision Support System, Deep Learning, Metaheuris-tics, BiLSTM, Feature selectionAbstract
Atherosclerosis is a pathological disorder that grows progressively over the years and might result in cardiac arrest, stroke, or a peripheral vascular ailment, based on the region of existence in the human arterial network. Earlier detection and classification of atherosclerosis becomes crucial in mitigating the severity of the disease and death rate. The recently developed artificial intelligence (AI) methods like machine learning (ML) and deep learning (DL) models ensured their efficiency in the design of medical decision support sys-tems (MDSS). In this view, this paper presents an early detection and classifi-cation of atherosclerosis using feature subset selection with optimal deep learning (EDCA-FSSODL) model. The proposed EDCA-FSSODL technique targets to decrease the dimensionality of the features and diagnose atherosclerosis. The proposed EDCA-FSSODL technique derives a novel binary chaotic flower pollination algorithm (BCFPA) based feature selection to eliminate the curse of dimensionality problem. In addition, Manta ray Foraging Optimization (MRFO) with bidirectional long short-term memory (BiLSTM) method is implemented for classifying and recognizing atherosclerosis disease. Moreover, the utilization of MRFO method assists in the appropriate tuning of the hyperparameters of the BiLSTM technique and thus boosts the overall recognition performance. To portray the improved accomplishment of the EDCA-FSSODL technique, a sequence of simulations occurs by employing two standard datasets and validate the outputs using different measures. Overall relative research highlighted the supremacy of the EDCA-FSSODL technique over the other approaches
References
Terrada, O., Cherradi, B., Raihani, A. and Bouattane, O., 2020. A novel medical diagnosis support system for predicting patients with atherosclerosis diseases. Informatics in Medicine Unlocked, 21, p.100483
V.S.H. Rao, M.N. Kumar, Novel approaches for predicting risk factors of atherosclerosis, IEEE J. Biomed. Health Inform. 17 (2012) 183–189
J.J. Batzel, M. Bachar, F. Kappel, Mathematical Modeling and Validation in Physiology: Applications to the Cardiovascular and Respiratory Systems, vol. 2064, Springer, 2012
B. Iba nez, J.J. Badimon, M.J. Garcia, Diagnosis of atherosclerosis by imaging, Am. J. Med. 122 (2009) S15–S25
Daanouni O, Cherradi B, Tmiri A. Type 2 diabetes mellitus prediction model based on machine learning ap-proach. In: Ben Ahmed M, Boudhir AA, Santos D, El Aroussi M, Karas ˙ IR, editors. In Innovations in smart cit-ies applications edition 3. Cham: Springer International Publishing; 2020. p. 454–69
Abdar M, Acharya UR, Sarrafzadegan N, Makarenkov V. NE-nu-SVC: a new nested ensemble clinical deci-sion support system for effective diagnosis of coronary artery disease. IEEE Access 2019;7:167605–20
Terrada O, Cherradi B, Raihani A, Bouattane O. A fuzzy medical diagnostic support system for cardiovascu-lar diseases diagnosis using risk factors. In: 2018 international Conference on electronics, control, Optimiza-tion and computer science (ICECOCS); Dec. 2018. p. 1–6
Nasarian E, et al. Association between work-related features and coronary artery disease: a heterogeneous hybrid feature selection integrated with balancing approach. Pattern Recogn Lett May 2020;133:33–40
Y. Hu, L. Li, L. Shen, H. Gao, The relationship between arterial wall stiffness and left ventricular dysfunction, Neth. Heart J. 21 (2013) 222–227
Jain, K., Jain, S., Guha, A. and Patra, A., 2021. An approach to early stage detection of atherosclerosis using arterial blood pressure measurements. Biomedical Signal Processing and Control, 68, p.102594
Upretee, P. and Yüksel, M.E., 2021. Accurate classification of heart sounds for disease diagnosis by us-ing spectral analysis and deep learning methods. In Data Analytics in Biomedical Engineering and Healthcare (pp. 215-232). Academic Press
Kumar, B. and Mathur, H., 2021. Comprehensive Analysis of Atherosclerosis Disease Prediction using Machine Learning. Annals of the Romanian Society for Cell Biology, pp.17962-17975
Fan, J., Chen, M., Luo, J., Yang, S., Shi, J., Yao, Q., Zhang, X., Du, S., Qu, H., Cheng, Y. and Ma, S., 2021. The prediction of asymptomatic carotid atherosclerosis with electronic health records: a comparative study of six machine learning models. BMC medical informatics and decision making, 21(1), pp.1-9
Demchenko, M. and Kashirina, I., 2020. The Use of Machine Learning Methods to the Automated Ath-erosclerosis Diagnostic and Treatment System Development
Kigka, V.I., Sakellarios, A.I., Mantzaris, M.D., Tsakanikas, V.D., Potsika, V.T., Palombo, D., Montecucco, F. and Fotiadis, D.I., 2021, November. A Machine Learning Model for the Identification of High risk Carotid Atherosclerotic Plaques. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 2266-2269). IEEE
Terrada, O., Cherradi, B., Raihani, A. and Bouattane, O., 2019, April. Classification and Prediction of atherosclerosis diseases using machine learning algorithms. In 2019 5th International Conference on Optimi-zation and Applications (ICOA) (pp. 1-5). IEEE
Khare, N., Devan, P., Chowdhary, C.L., Bhattacharya, S., Singh, G., Singh, S. and Yoon, B., 2020. Smo-dnn: Spider monkey optimization and deep neural network hybrid classifier model for intrusion detec-tion. Electronics, 9(4), p.692
Yang, X.S., 2012, September. Flower pollination algorithm for global optimization. In International conference on unconventional computing and natural computation (pp. 240-249). Springer, Berlin, Heidelberg
Nguyen, T.T., Pan, J.S. and Dao, T.K., 2019. An improved flower pollination algorithm for optimizing layouts of nodes in wireless sensor network. Ieee Access, 7, pp.75985-75998
Cai, Z., Gu, J., Wen, C., Zhao, D., Huang, C., Huang, H., Tong, C., Li, J. and Chen, H., 2018. An intelligent Parkinson’s disease diagnostic system based on a chaotic bacterial foraging optimization enhanced fuzzy KNN approach. Computational and mathematical methods in medicine, 2018
Rodrigues, D., Yang, X.-S., Souza, A. N., and Papa, J. P. (2015). Binary flower pollination algorithm and its application to feature selection. In Yang, X.-S., editor, Recent Advances in Swarm Intelligence and Evolu-tionary Computation, volume 585 of Studies in Computational Intelligence, pages 85–100. Springer Interna-tional Publishing
Khan, N.; Ullah, A.;Haq, I.U.; Menon, V.G.; Baik, S.W.; SD-Net: Understanding overcrowded scenes in real-time via an efficient dilated convolutional neural network. J. Real-Time Image Process. 2021, 18, 1729–1743
Zhao, W., Zhang, Z., Wang, L., 2020. Manta ray foraging optimization: An effective bio-inspired optimizer for engineering applications. Eng. Appl. Artif. Intell. 87, 103300
Hassan, M.H., Houssein, E.H., Mahdy, M.A. and Kamel, S., 2021. An improved manta ray foraging optimizer for cost-effective emission dispatch problems. Engineering Applications of Artificial Intelligence, 100, p.104155
https://archive.ics.uci.edu/ml/datasets.php
Gárate-Escamila, A.K., El Hassani, A.H. and Andrès, E., 2020. Classification models for heart disease prediction using feature selection and PCA. Informatics in Medicine Unlocked, 19, p.100330.
