{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T11:51:57Z","timestamp":1789732317900,"version":"4.0.1"},"reference-count":42,"publisher":"Institution of Engineering and Technology (IET)","issue":"6","license":[{"start":{"date-parts":[[2020,12,9]],"date-time":"2020-12-09T00:00:00Z","timestamp":1607472000000},"content-version":"vor","delay-in-days":8,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Healthcare Tech Letters"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:p>Electrocardiogram (ECG) signal is one of the most reliable methods to analyse the cardiovascular system. In the literature, there are different deep learning architectures proposed to detect various types of tachycardia diseases, such as atrial fibrillation, ventricular fibrillation, and sinus tachycardia. Even though all types of tachycardia diseases have fast beat rhythm as the common characteristic feature, existing deep learning architectures are trained with the corresponding disease\u2010specific features. Most of the proposed works lack the interpretation and understanding of the results obtained. Hence, the objective of this letter is to explore the features learned by the deep learning models. For the detection of the different types of tachycardia diseases, the authors used a transfer learning approach. In this method, the model is trained with one of the tachycardia diseases called atrial fibrillation and tested with other tachycardia diseases, such as ventricular fibrillation and sinus tachycardia. The analysis was done using different deep learning models, such as RNN, LSTM, GRU, CNN, and RSCNN. RNN achieved an accuracy of 96.47% for atrial fibrillation data set, 90.88% accuracy for CU\u2010ventricular tachycardia data set, and also achieved an accuracy of 94.71, and 94.18% for MIT\u2010BIH malignant ventricular ectopy database for ECG lead I and lead II, respectively. The RNN model could only achieve an accuracy of 23.73% for the sinus tachycardia data set. A similar trend is shown by other models. From the analysis, it was evident that even though tachycardia diseases have fast beat rhythm as their common feature, the model was not able to detect different types of tachycardia diseases. The deep learning model could only detect atrial fibrillation and ventricular fibrillation and failed in the case of sinus tachycardia. From the analysis, they were able to interpret that, along with the fast beat rhythm, the model has learned the absence of P\u2010wave which is a common feature for ventricular fibrillation and atrial fibrillation but sinus tachycardia disease has an upright positive P\u2010wave. The time\u2010based analysis is conducted to find the time complexity of the models. The analysis conveyed that RNN and RSCNN models could achieve better performance with lesser time complexity.<\/jats:p>","DOI":"10.1049\/htl.2020.0033","type":"journal-article","created":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T21:26:56Z","timestamp":1607635616000},"page":"146-154","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Explainable artificial intelligence for heart rate variability in ECG signal"],"prefix":"10.1049","volume":"7","author":[{"given":"Sanjana","family":"K.","sequence":"first","affiliation":[{"name":"Center for Computational Engineering and Networking Amrita School of Engineering, Amrita Vishwa Vidyapeetham  Coimbatore Tamilnadu India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3745-6944","authenticated-orcid":false,"given":"Sowmya","family":"V.","sequence":"additional","affiliation":[{"name":"Center for Computational Engineering and Networking Amrita School of Engineering, Amrita Vishwa Vidyapeetham  Coimbatore Tamilnadu India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gopalakrishnan","family":"E.A.","sequence":"additional","affiliation":[{"name":"Center for Computational Engineering and Networking Amrita School of Engineering, Amrita Vishwa Vidyapeetham  Coimbatore Tamilnadu India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soman","family":"K.P.","sequence":"additional","affiliation":[{"name":"Center for Computational Engineering and Networking Amrita School of Engineering, Amrita Vishwa Vidyapeetham  Coimbatore Tamilnadu India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"265","published-online":{"date-parts":[[2020,12,9]]},"reference":[{"key":"e_1_2_6_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/0002\u20109149(70)90004\u20104"},{"key":"e_1_2_6_3_2","doi-asserted-by":"crossref","unstructured":"BuettnerR. SchunterM.: \u2018Efficient machine learning based detection of heart disease\u2019.Proc. IEEE Healthcom Bogota Colombia 2019","DOI":"10.1109\/HealthCom46333.2019.9009429"},{"key":"e_1_2_6_4_2","unstructured":"https:\/\/www.hrsonline.org\/patient\u2010resources\/heartdiseases\u2010disorders"},{"key":"e_1_2_6_5_2","unstructured":"RajpurkarP. HannunA. Y. HaghpanahiM.et al.: \u2018Cardiologist\u2010level arrhythmia detection with convolutional neural networks\u2019 arXiv preprint arXiv:1707.01836 2017"},{"key":"e_1_2_6_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0092\u20108674(01)00243\u20104"},{"key":"e_1_2_6_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/0002\u20109149(84)90247\u20109"},{"key":"e_1_2_6_8_2","doi-asserted-by":"publisher","DOI":"10.1136\/hrt.33.5.742"},{"key":"e_1_2_6_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/0002\u20109149(73)90302\u20100"},{"key":"e_1_2_6_10_2","unstructured":"BraunwaldE.: \u2018Heart disease\u2019 1988"},{"key":"e_1_2_6_11_2","unstructured":"KutluY. AltanG. AllahverdiN.: \u2018Arrhythmia classification using waveform ecg signals\u2019.Int. Conf. Advanced Technology & Sciences Konya Turkey 2016"},{"key":"e_1_2_6_12_2","unstructured":"SubramanianB.: \u2018Ecg signal classification and parameter estimation using multiwavelet transform\u2019 2017"},{"key":"e_1_2_6_13_2","first-page":"62","article-title":"A method for acquisition and processing of electrophysiological signals on computer. The case of ecg signal","author":"Popa R.","year":"1996","journal-title":"Annals of \u2018Dunarea de Jos\u2019 University of Galati"},{"key":"e_1_2_6_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.08.022"},{"key":"e_1_2_6_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.04.012"},{"key":"e_1_2_6_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/10.942588"},{"key":"e_1_2_6_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2014.04.001"},{"key":"e_1_2_6_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2013.08.008"},{"key":"e_1_2_6_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2005.856281"},{"issue":"6","key":"e_1_2_6_20_2","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1109\/TBME.2013.2275000","article-title":"Ventricular fibrillation and tachycardia classification using a machine learning approach","volume":"61","author":"Li Q.","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"e_1_2_6_21_2","doi-asserted-by":"crossref","unstructured":"AssodikyH. SyarifI. BadriyahT.: \u2018Deep learning algorithm for arrhythmia detection\u2019.2017 Int. Electronics Symp. on Knowledge Creation and Intelligent Computing (IES\u2010KCIC) Surabaya Indonesia 2017 pp.26\u201332","DOI":"10.1109\/KCIC.2017.8228452"},{"key":"e_1_2_6_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.11.238"},{"key":"e_1_2_6_23_2","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2019.00103"},{"key":"e_1_2_6_24_2","unstructured":"GeeA.H. Garcia\u2010OlanoD. GhoshJ.et al.: \u2018Explaining deep classification of time\u2010series data with learned prototypes\u2019 arXiv preprint arXiv:1904.08935 2019"},{"key":"e_1_2_6_25_2","doi-asserted-by":"crossref","unstructured":"AndreottiF. CarrO. PimentelM.A.et al.: \u2018Comparing feature\u2010based classifiers and convolutional neural networks to detect arrhythmia from short segments of ecg\u2019.2017 Computing in Cardiology (CinC) Rennes France 2017 pp.1\u20134","DOI":"10.22489\/CinC.2017.360-239"},{"key":"e_1_2_6_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.08.011"},{"key":"e_1_2_6_27_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010018\u20100268\u20103"},{"key":"e_1_2_6_28_2","doi-asserted-by":"crossref","unstructured":"ShashikumarS.P. ShahA.J. CliffordG.D.et al.: \u2018Detection of paroxysmal atrial fibrillation using attention\u2010based bidirectional recurrent neural networks\u2019.Proc. of the 24th ACM SIGKDD Int. Conf. on Knowledge Discovery & Data Mining London UK 2018 pp.715\u2013723","DOI":"10.1145\/3219819.3219912"},{"key":"e_1_2_6_29_2","doi-asserted-by":"crossref","unstructured":"SujadeviV. SomanK. VinayakumarR.: \u2018Realtime detection of atrial fibrillation from short time single lead ecg traces using recurrent neural networks\u2019.The Int. Symp. on Intelligent Systems Technologies and Applications Manipal India 2017 pp.212\u2013221","DOI":"10.1007\/978-3-319-68385-0_18"},{"key":"e_1_2_6_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2468589"},{"key":"e_1_2_6_31_2","doi-asserted-by":"crossref","unstructured":"KachueeM. FazeliS. SarrafzadehM.: \u2018Ecg heartbeat classification: a deep transferable representation\u2019.2018 IEEE Int. Conf. on Healthcare Informatics (ICHI) New York NY USA 2018 pp.443\u2013444","DOI":"10.1109\/ICHI.2018.00092"},{"key":"e_1_2_6_32_2","doi-asserted-by":"crossref","unstructured":"GopikaP. SowmyaV. GopalakrishnanE.et al.: \u2018Performance improvement of residual skip convolutional neural network for myocardial disease classification\u2019.Int. Conf. on Intelligent Computing and Communication Technologies Hyderabad India 2019 pp.226\u2013234","DOI":"10.1007\/978-981-13-8461-5_25"},{"key":"e_1_2_6_33_2","unstructured":"HolzingerA. BiemannC. PattichisC. S.et al.: \u2018What do we need to build explainable ai systems for the medical domain?\u2019 arXiv preprint arXiv:1712.09923 2017"},{"key":"e_1_2_6_34_2","doi-asserted-by":"crossref","unstructured":"LepageR. BoucherJ.\u2010M. BlancJ.\u2010J.et al.: \u2018Ecg segmentation and p\u2010wave feature extraction: application to patients prone to atrial fibrillation\u2019.2001 Conf. Proc. of the 23rd Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society Istanbul Turkey 2001 vol. 1 pp.298\u2013301","DOI":"10.1109\/IEMBS.2001.1018918"},{"key":"e_1_2_6_35_2","volume-title":"The development and analysis of a ventricular fibrillation detector","author":"Greenwald S.D.","year":"1986"},{"key":"e_1_2_6_36_2","doi-asserted-by":"publisher","DOI":"10.1046\/j.1460\u20109592.2001.00217.x"},{"key":"e_1_2_6_37_2","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.101.23.e215"},{"key":"e_1_2_6_38_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2017.00258"},{"key":"e_1_2_6_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.05.041"},{"key":"e_1_2_6_40_2","doi-asserted-by":"crossref","unstructured":"ChanthercrobJ. MahattanataweeS. TeeramongkonrasmeeA.et al.: \u2018Development of rhythm\u2010based and morphology\u2010based algorithm for atrial fibrillation detection from single lead ecg signal\u2019.2020 8th Int. Electrical Engineering Congress (iEECON) Chiang Mai Thailand 2020 pp.1\u20134","DOI":"10.1109\/iEECON48109.2020.229484"},{"key":"e_1_2_6_41_2","unstructured":"BoreikoM.: \u2018Development of advanced method for heart ventricular fibrillation detection\u2019 2019"},{"key":"e_1_2_6_42_2","doi-asserted-by":"crossref","unstructured":"SohailM.A. TaufiqueZ. AbubakarS.M.et al.: \u2018An ecg processor for the detection of eight cardiac arrhythmias with minimum false alarms\u2019.2019 IEEE Biomedical Circuits and Systems Conf. (BioCAS) Nara Japan 2019 pp.1\u20134","DOI":"10.1109\/BIOCAS.2019.8919053"},{"key":"e_1_2_6_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11045\u2010019\u201000651\u2010w"}],"container-title":["Healthcare Technology Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/htl.2020.0033","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/htl.2020.0033","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/htl.2020.0033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T07:21:15Z","timestamp":1761636075000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/htl.2020.0033"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["10.1049\/htl.2020.0033"],"URL":"https:\/\/doi.org\/10.1049\/htl.2020.0033","archive":["Portico"],"relation":{},"ISSN":["2053-3713","2053-3713"],"issn-type":[{"value":"2053-3713","type":"print"},{"value":"2053-3713","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]},"assertion":[{"value":"2020-04-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-10-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-12-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}