d847786c-6b0f-4b6e-b598-42f9c6f04c6e20220727093309738naun:naunmdt@crossref.orgMDT DepositInternational Journal of Biology and Biomedical Engineering1998-451010.46300/91011http://www.naun.org/cms.action?id=3041110202211020221610.46300/91011.2022.16https://npublications.com/journals/bio/2022.phpST-based Deep Learning Analysis of COVID-19 PatientsFrikhaHounaidaNational School of Electronics and Telecommunications of Sfax, TunisiaOdetteFokapuUniversity of Picardie Jules Verne, LTI, Cuffies-Soissons, FranceChrifi-AlaouiLarbiUniversity of Picardie Jules Verne, LTI, Cuffies-Soissons, FranceMeddeb MakhloufAmelNational School of Electronics and Telecommunications of Sfax, TunisiaZaraiFaouziNational School of Electronics and Telecommunications of Sfax, TunisiaThe number of deaths worldwide caused by COVID-19 continues to increase and the variants of the virus whose process we do not yet master are aggravating this situation. To deal with this global pandemic, early diagnosis has become important. New investigation methods are needed to improve diagnostic performance. A very large number of patients with COVID-19 have with cardiac arrhythmias often with ST segment elevation or depression on an electrocardiogram. Can ST-segment changes contribute to automatic diagnosis of COVID-19? In this article, we have tried to answer this question. We propose in this work a method for the automatic identification of COVID patients which exploits in particular the modifications of the ST segment observed on recordings of the ECG signal. Two sources of data allowed the development of the database for this study: 300 ECGs from the "physioNet" database with prior measurement of the ST segments, and 100 paper ECGs of patients from the cardiology department of the hospital X in Tunis registered on (non-covid) topics and covid topics. Four learning algorithms (ANN, CNN-LSTM, Xgboost, Random forest) were then applied on this database. The evaluation results show that CNN-LSTM and Xgboost present better accuracy in terms of classifying covid and non-covid patients with an accuracy rate of 87% and 88.7% respectively.7272022727202232132939https://npublications.com/journals/bio/2022/a782010-039(2022).pdf10.46300/91011.2022.16.39https://npublications.com/journals/bio/2022/a782010-039(2022).pdf10.1016/s0140-6736(20)30183-5Huang C, Wang Y, Li X, Ren L, Zhao J, Hu Y, et al. Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. Lancet. 2020;395(10223):497–506. 10.1007/s00134-020-05993-9Zeng J, Huang J, Pan L. How to balance acute myocardial infarction and COVID-19: the protocols from Sichuan provincial People’s hospital. Intensive Care Med. 2020: 1–3. 10.1007/s00392-020-01626-9Bo Li, Jing Yang, Faming Zhao, Lili Zhi, Xiqian Wang, Lin Liu, Zhaohui Bi1, Yunhe Zhao, Prevalence and impact of cardiovascular metabolic diseases on COVID 19 in China, Clinical Research in Cardiology (2020) 109:531–538. 10.1001/jama.2020.1585Wang D, Hu B, Hu C, Zhu F, Liu X, Zhang J, et al. Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus-infected pneumonia in Wuhan, China. JAMA. 2020 ;323(11):1061–9. 10.1001/jamacardio.2020.1096Inciardi RM, Lupi L, Zaccone G, Italia L, Raffo M, Tomasoni D, et al. Cardiac involvement in a patient with coronavirus disease 2019 (COVID-19). JAMA Cardiol. 2020; 5(7):819–24. 10.1161/circulationaha.120.046941Clerkin KJ, Fried JA, Raikhelkar J, Sayer G, Griffin JM, Masoumi A, et al. Coronavirus disease 2019 (COVID19) and cardiovascular disease. Circulation. 2020;141(20): 1648–55. 10.1016/j.ahj.2020.05.006Dehghani et al, North American COVID-19 STSegment Elevation Myocardial Infarction (NACMI) registry: Rationale, design, and implications, (2020) American Heart Journal volume 227 https://www.cardio-online.fr/Actualites/Revues-de-lalitterature/COVID-19-et-systeme-cardiovasculaire 10.1016/j.procs.2016.04.266Rim Negraa, Imen Jemilia et AbdelfettahBelghitha “Wireless Body Area Networks: Applications and technologies “, Procedia Computer Science 83 ,2016, 1274 – 1281. Stefanini GG, Montorfano M, Trabattoni D, et al. STelevation myocardial infarction in patients with COVID19: clinical and angiographic outcomes. Circulation. 2020. 10.1016/j.ajem.2020.06.012Pranata et al, Potential role of telemedicine in solving ST-segment elevation dilemmas in remote areas during the COVID-19 pandemic, The American Journal of Emergency Medicine Volume 42, April 2021, Pages 242-243 10.1016/j.ajem.2020.10.005Hasan Ali Barman, AdemAtici, GokhanAlici a, Omer Sit, SevilTugrul, BarisGungor, ErtugrulOkuyan, Irfan Sahin, The effect of the severity COVID-19 infection on electrocardiography, American Journal of Emergency Medicine 46 (2021) 317–322 ,2020. Bangalore et al, ST-Segment Elevation in Patients with Covid-19 - A Case Series,the New England journal of medicine ,2020 10.21203/rs.3.rs-33824/v1Li L, Zhang S, He B, Chen X, Wang S, Zhao Q. Risk factors and electrocardiogram characteristics for mortality in critical inpatients with covid-19. ClinCardiol. 2020;43(12):1624–30. 10.1016/j.ejim.2020.06.015Angeli F, Spanevello A, De Ponti R, Visca D, Marazzato J, Palmiotto G, Feci D, Reboldi G, Fabbri LM, Verdecchia P. Electrocardiographic features of patients with covid-19 pneumonia. Eur J Intern Med. 2020; 78:101–6. 10.1016/j.ahj.2020.05.006Dehghani et al, North American COVID-19 ST-Segment Elevation Myocardial Infarction (NACMI) registry: Rationale, design, and implications, (2020) American Heart Journal volume 227 10.1111/anec.12806Wang Y, Chen L, Wang J, He X, Huang F, Chen J, Yang X. Electrocardiogram analysis of patients with different types of covid-19. Ann Noninvasive Electrocardiol. 2020;25(6):12806. 10.1016/j.cardfail.2020.06.005McCullough SA, Goyal P, Krishnan U, Choi JJ, Saford MM, Okin PM. Electrocardiographic findings in covid19: insights on mortality and underlying myocardial processes. J Card Fail. 2020; 26:626–32. AbdelouahebFarhi,segment ST,janvier 2019 ,ecgformation.com 10.1093/europace/euaa258Bertini M, Ferrari R, Guardigli G, Malagù M, Vitali F, Zucchetti O, D’Aniello E, Volta CA, Cimaglia P, Piovaccari G, et al. Electrocardiographic features of 431 consecutive, critically ill covid-19 patients: an insight into the mechanisms of cardiac involvement. EP Eur. 2020;22(12):1848–54. 10.1016/j.ajem.2020.10.005Hasan Ali Barman, AdemAtici, GokhanAlici a, Omer Sit, SevilTugrul, BarisGungor, ErtugrulOkuyan, Irfan Sahin, The effect of the severity COVID-19 infection on electrocardiography, American Journal of Emergency Medicine 46 (2021) 317–322,2020. 10.3390/s19122780Muhammad E. H. Chowdhury, KhawlaAlzoubi, AmithKhandakar, RidabKhallifa, RayaanAbouhasera, Sirine Koubaa, Rashid Ahmed, Anwarul Hasan, Wearable Real-Time Heart Attack Detection and Warning System to Reduce Road Accidents,2019. 10.1016/j.jeur.2009.02.001Erwin Christian, de Bliek,"Élévation ST : diagnostic différentiel et mises en garde. Une revue complète pour aider à distinguer l'infarctus du myocarde avec élévation ST des étiologies non ischémiques de l'élévation ST". Journal turc de médecined'urgence. 18(1) : 1-10,2018. 10.1016/j.cmpb.2018.04.005Faust, O., Hagiwara, Y., Hong, T.J., Lih, O.S. and Acharya, U.R. Deep learning for healthcare applications based on physiological signals: A review. Computer methods and programs in biomedicine, 161, pp.1- 13,2018. 10.1109/secon.2016.7506757Alba-Flores, R., Hickman, S. and Mirzakani, A.S., March. Performance analysis of two ANN based classifiers for EMG signals to identify hand motions. In Southeast Con 2016 (pp. 1-5). IEEE, 2016. 10.1007/978-3-030-02674-5_7Selvakanmani, S., Shanmathi, M. and Sandhya, N.S. Cluster-Based Health Monitoring Scheme in Wireless Sensor Networks. In Computational Intelligence and Sustainable Systems (pp. 99-113). Springer, Cham, 2019. 10.1109/wetice49692.2020.00032Frikha Hounaida; Ben daoud Wided; Meddeb-Makhoulf Amel; Zarai Faouzi, A Learning based Secure Anomaly Detection for Healthcare Applications, IEEE, WETICE,2020. 10.1016/j.cmpb.2018.04.005Faust, O., Hagiwara, Y., Hong, T.J., Lih, O.S. and Acharya, U.R. Deep learning for healthcare applications based on physiological signals: A review. Computer methods and programs in biomedicine, 161, pp.1-13 ,2018. DEKAI WAH, Abuser detection random forest model and hyper parameter tuning, Line engineering ,2020. 10.1093/europace/euaa258Bertini M, Ferrari R, Guardigli G, Malagù M, Vitali F, Zucchetti O, D’Aniello E, Volta CA, Cimaglia P, Piovaccari G, et al. Electrocardiographic features of 431 consecutive, critically ill covid-19 patients: an insight into the mechanisms of cardiac involvement. EP Eur. 2020;22(12):1848–54. Nemati R, Ganjoo M, Jadidi F, Tanha A, Baghbani R. Electrocardiography in early diagnosis of cardiovascular complications of covid-19; a systematic literature review. Arch AcadEmerg Med. 2021. 10.1007/s10509-019-3602-4Yuanchao Wang, Z. Pan, J. Zheng, L. Qian, A hybrid ensemble method for pulsar candidate classification, Astrophysics and Space Science ,2019. Ashley C,An Overview on Convolutional Neural Networks, start it up ,2020. 10.1016/j.compbiomed.2018.06.002S.L. Oh, E.Y.K. Ng, R.S. Tan, U.R. Acharya, Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats, Computers in Biology and Medicine 102 (2018) 278–287. 10.3390/s20185037HishamElMoaqet, Mohammad Eid, Martin Glos ,MutazRyalat and Thomas Penzel , Deep Recurrent Neural Networks for Automatic Detection of Sleep Apnea from Single Channel Respiration Signals,Sensors,2020. Togha M, Sharifpour A, Ashraf H, Moghadam M, Sahrian MA,"Anomalies électrocardiographiques dans les événements cérébrovasculaires aigus chez les patients avec/sans maladie cardiovasculaire ». Annales de l'Académie indienne de neurologie. 16 (1): 66-71. 2013 10.1016/j.chaos.2020.110120Talha Burak Alakus, Ibrahim Turkoglu, Chaos, Solitons and Fractals Nonlinear Science, and Nonequilibrium and Complex Phenomena, (2020), Comparison of deep learning approaches to predict COVID-19 infection. 10.1016/j.ymssp.2020.106885RuoyuYangShubhendu Kumar SinghMostafaTavakkoliNiktaAmiriYongchaoYangM. Amin KaramiRahulRai,” CNN-LSTM deep learning architecture for computervision-based modal frequency detection”,,Mechanical Systems and Signal Processingjournal ,2020. Rob Harrand,Kagglekernels:what causes heart-disease, 2019 .