A hybrid recurrent neural network ‐ logistic chaos‐based whale optimization framework for heart disease prediction with electronic health records

A hybrid recurrent neural network ‐ logistic chaos‐based whale optimization framework for heart disease prediction with electronic health records P. Priyanga Department of Computer Science and Engineering Global Academy of Technology, VTU Bangalore India https://orcid.org/0000-0001-9323-7514 Veena V. Pattankar Department of Computer Science and Engineering Global Academy of Technology, VTU Bangalore India S. Sridevi Department of Computer Science and Engineering VISTAS Chennai India Abstract

Heart disease, known interchangeably as “Cardio Vascular Disease,” blocks the blood vessels in the heart and causes heart attack, chest pain, and stroke. Heart disease is one of the leading causes of morbidity and mortality worldwide and it is one of the major causes of morbidity and mortality globally and a trending topic in clinical data analysis. Assessing risk factors related to heart disease is considered as an important step in diagnosing the disease at an early stage. Clinical data present in the form of electronic health records (EHR) can be extracted with the aid of machine learning (ML) algorithms to provide valuable decisions and predictions. ML approaches also play a vital role in early diagnosis and therapeutic monitoring of heart disease. Several research works have been carried out recently to predict heart disease. To this end, we propose a novel hybrid recurrent neural network (RNN)‐logistic chaos‐based whale optimization (LCBWO) structured hybrid framework for predicting heart disease within 5 years using EHR data. Meanwhile, in the hybrid model established multilayer bidirectional LSTM is used for feature selection, LCBWO algorithm for structural improvement and fast convergence, and LSTM for disease prediction. This research used 10 cross‐validations to obtain generalized accuracy and error values. The findings and observations provided here are focused on the knowledge obtained from the EHR report. The results show that the proposed novel hybrid RNN‐LCBWO framework achieves a higher accuracy of 98%, a specificity of 99%, precision of 96%, Mathews correlation coefficient of 91%, F‐measure of 0.9892, an area under the curve value of 98%, and a prediction time of 9.23 seconds. The accurate predictions obtained from the comparative analysis shows the significant performance of our proposed framework.
10 2020 02 2021 315 343 10.1111/coin.12405 2 10.1002/crossmark_policy onlinelibrary.wiley.com true 2020-04-25 2020-08-02 2020-10-01 http://onlinelibrary.wiley.com/termsAndConditions#vor 10.1111/coin.12405 https://onlinelibrary.wiley.com/doi/10.1111/coin.12405 https://onlinelibrary.wiley.com/doi/pdf/10.1111/coin.12405 https://onlinelibrary.wiley.com/doi/pdf/10.1111/coin.12405 https://onlinelibrary.wiley.com/doi/full-xml/10.1111/coin.12405 Global Status Report on Noncommunicable Diseases in 2014 World Health Organization 2014 National Vital Statistics Reports H Melonie 2019 10.1161/CIR.0000000000000659 10.4103/HEARTVIEWS.HEARTVIEWS_106_17 10.1007/978-981-13-1071-3_10 10.1007/978-3-319-11680-8_46 Biomed Res Uma D 2646 29 12 2018 Prediction system for heart disease using naive Bayes and particle swarm optimization 10.1109/ACCESS.2019.2909969 10.1016/j.protcy.2013.12.340 10.1109/ICoAC.2013.6921957 Bhuvaneswari AmmaNG. An intelligent approach based on principal component analysis and adaptive neuro fuzzy inference system for predicting the risk of cardiovascular diseases. Paper presented at: 2013 Fifth International Conference on Advanced Computing (ICoAC) Vol. 2013; 2013;241‐245; Chennai. 10.1109/ACCESS.2019.2904800 10.1109/CIMCA.2014.7057817 MurthyHN MeenakshiM. Dimensionality reduction using neuro‐genetic approach for early prediction of coronary heart disease. Paper presented at: International Conference on Circuits Communication Control and Computing; 2014; 329‐332; IEEE: Bangalore India. 10.1109/ACCESS.2017.2789324 10.1007/978-81-322-1759-6_81 ChitraR SeenivasagamVRisk prediction of heart disease based on swarm optimized neural network. Paper presented at: Proceedings of International Conference on Computer Science and Information Technology; 2014;707‐714; New Delhi: Springer. 10.1016/j.eswa.2008.09.013 10.1007/978-981-10-0266-3_37 YazdaniA RamakrishnanK. Performance evaluation of artificial neural network models for the prediction of the risk of heart disease. Paper presented at: International Conference for Innovation in Biomedical Engineering and Life Sciences; 2015;179‐182. 10.1016/j.compbiomed.2017.09.011 10.1016/j.eswa.2016.10.020 10.1007/s10489-017-1037-6 10.1007/978-3-319-46681-1_42 YaoY HuangZ. Bi‐directional LSTM recurrent neural network for Chinese word segmentation. Paper presented at: International Conference on Neural Information Processing; 2016;345‐353; Cham: Springer. ChenG. A gentle tutorial of recurrent neural network with error backpropagation.arxiv.org/abs/1610.02583; 2018. 10.1109/NEUREL.2018.8586990 SunQ JankovicMV BallyL MougiakakouSG. Predicting blood glucose with an LSTM and bi‐LSTM based deep neural network. Paper presented at: 2018 14th Symposium on Neural Networks and Applications (NEUREL); 2018. 10.1136/amiajnl-2013-002214 10.1016/j.jbi.2015.05.009 10.1002/047084535X 10.1109/78.650093 10.1109/ASRU.2013.6707742 GravesA JaitlyN MohamedA. Hybrid speech recognition with deep bidirectional LSTM. Paper presented at: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding; 2013;273‐278; Olomouc. 10.1016/j.advengsoft.2016.01.008 The Humpback Whale. Cetacean Societies, Field Studies of Dolphins and Whales Clapham PJ 173 2000 10.1080/15397734.2016.1213639 10.3390/systems4040037 10.1007/s00500-016-2360-2 10.1016/j.bspc.2019.101728 10.1093/ptj/85.3.257 10.1162/neco.1997.9.8.1735 10.11613/BM.2012.031 10.1109/CSNT.2013.21 MishraBK LakkadwalaP ShrivastavaNK. Novel approach to predict cardiovascular disease using incremental SVM. Paper presented at: 2013 International Conference on Communication Systems and Network Technologies; 2013;55‐59; IEEE: Gwalior India. Appl Math Sci Wisaeng K 4103 8 2014 Predict the diagnosis of heart disease using feature selection and k‐nearest neighbor algorithm 10.1186/s12911-019-0765-4 10.1108/IJCS-01-2019-0002 KennedyJ EberhartR. Particle swarm optimization. Paper presented at: Proceedings of the IEEE International Conference on Neural Networks; Perth WA Australia. 1995;19421948. 10.1016/j.advengsoft.2013.12.007 Progress in Photovoltaics: Research and Applications Vinu S 2020 CCGPA‐MPPT: Cauchy preferential crossover‐based global pollination algorithm for MPPT in photovoltaic system 10.1504/IJBET.2019.103242 10.1007/s11277-018-6014-9 10.1016/j.cose.2018.04.009 10.1007/s11042-019-7577-5 10.22266/ijies2016.0930.12