{"id":"https://openalex.org/W7125970777","doi":"https://doi.org/10.48550/arxiv.2601.18830","title":"How Much Temporal Modeling is Enough? A Systematic Study of Hybrid CNN-RNN Architectures for Multi-Label ECG Classification","display_name":"How Much Temporal Modeling is Enough? A Systematic Study of Hybrid CNN-RNN Architectures for Multi-Label ECG Classification","publication_year":2026,"publication_date":"2026-01-25","ids":{"openalex":"https://openalex.org/W7125970777","doi":"https://doi.org/10.48550/arxiv.2601.18830"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2601.18830","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124095588","display_name":"Alireza Jafari","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jafari, Alireza","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124114027","display_name":"Fatemeh Jafari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jafari, Fatemeh","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124095588"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11021","display_name":"ECG Monitoring and Analysis","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11021","display_name":"ECG Monitoring and Analysis","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10065","display_name":"Atrial Fibrillation Management and Outcomes","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7192999720573425},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6751999855041504},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5370000004768372},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5067999958992004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45879998803138733},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44200000166893005},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4372999966144562},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.37130001187324524}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7192999720573425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024000287055969},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6751999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6003000140190125},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5370000004768372},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.30559998750686646},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2601.18830","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2601.18830","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.18830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2601.18830","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"multi-label":[1,82],"classification":[2,84],"of":[3,13,43,61,205,217],"electrocardiogram":[4],"(ECG)":[5],"signals":[6],"remains":[7],"challenging":[8],"due":[9,188],"to":[10,107,111,189],"the":[11,38,86,130,201],"coexistence":[12],"multiple":[14,68],"cardiac":[15],"conditions,":[16],"pronounced":[17],"class":[18],"imbalance,":[19],"and":[20,34,40,77,114,137,152,184,192,220],"long-range":[21],"temporal":[22,112,203],"dependencies":[23],"in":[24],"multi-lead":[25],"recordings.":[26],"Although":[27,161],"recent":[28],"studies":[29],"increasingly":[30],"rely":[31],"on":[32,85],"deep":[33],"stacked":[35,79,162],"recurrent":[36,69,102,159,163,179,211],"architectures,":[37],"necessity":[39],"clinical":[41],"justification":[42],"such":[44],"architectural":[45,198],"complexity":[46],"have":[47],"not":[48],"been":[49],"rigorously":[50],"examined.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"perform":[56],"a":[57,98,121,125,214],"systematic":[58],"comparative":[59],"evaluation":[60],"convolutional":[62],"neural":[63],"networks":[64],"(CNNs)":[65],"combined":[66],"with":[67,124,157,200],"configurations,":[70],"including":[71],"LSTM,":[72],"GRU,":[73],"Bidirectional":[74],"LSTM":[75],"(BiLSTM),":[76],"their":[78,109],"variants,":[80],"for":[81,168],"ECG":[83,206],"PTB-XL":[87],"dataset":[88],"comprising":[89],"23":[90],"diagnostic":[91],"categories.":[92],"The":[93],"CNN":[94,122],"component":[95],"serves":[96],"as":[97],"morphology-driven":[99],"baseline,":[100],"while":[101],"layers":[103],"are":[104],"progressively":[105],"integrated":[106,123],"assess":[108],"contribution":[110],"modeling":[113],"generalization":[115,187],"performance.":[116],"Experimental":[117],"results":[118,173],"indicate":[119],"that":[120,177,197],"single":[126],"BiLSTM":[127],"layer":[128],"achieves":[129],"most":[131],"favorable":[132],"trade-off":[133],"between":[134],"predictive":[135],"performance":[136,219],"model":[138],"complexity.":[139],"This":[140],"configuration":[141],"attains":[142],"superior":[143],"Hamming":[144],"loss":[145],"(0.0338),":[146],"macro-AUPRC":[147],"(0.4715),":[148],"micro-F1":[149],"score":[150],"(0.6979),":[151],"subset":[153],"accuracy":[154],"(0.5723)":[155],"compared":[156],"deeper":[158],"combinations.":[160],"models":[164],"occasionally":[165],"improve":[166],"recall":[167],"specific":[169],"rare":[170],"classes,":[171],"our":[172],"provide":[174],"empirical":[175],"evidence":[176],"increasing":[178],"depth":[180],"yields":[181],"diminishing":[182],"returns":[183],"may":[185],"degrade":[186],"reduced":[190],"precision":[191],"overfitting.":[193],"These":[194],"findings":[195],"suggest":[196],"alignment":[199],"intrinsic":[202],"structure":[204],"signals,":[207],"rather":[208],"than":[209],"increased":[210],"depth,":[212],"is":[213],"key":[215],"determinant":[216],"robust":[218],"clinically":[221],"relevant":[222],"deployment.":[223]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-01-29T00:00:00"}