{"id":"https://openalex.org/W4415648726","doi":"https://doi.org/10.1109/tcbbio.2025.3626210","title":"A Novel Vision Transformer Based Multimodal Fusion Approach for Clinical MDD Diagnosis Using EEG and Audio Signals","display_name":"A Novel Vision Transformer Based Multimodal Fusion Approach for Clinical MDD Diagnosis Using EEG and Audio Signals","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415648726","doi":"https://doi.org/10.1109/tcbbio.2025.3626210","pmid":"https://pubmed.ncbi.nlm.nih.gov/41144409"},"language":"en","primary_location":{"id":"doi:10.1109/tcbbio.2025.3626210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3626210","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091587843","display_name":"Sagnik De","orcid":"https://orcid.org/0009-0004-3092-5319"},"institutions":[{"id":"https://openalex.org/I106542073","display_name":"University of Calcutta","ror":"https://ror.org/01e7v7w47","country_code":"IN","type":"education","lineage":["https://openalex.org/I106542073"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sagnik De","raw_affiliation_strings":["Institute of Radio Physics & Electronics, University of Calcutta, Kolkata, India"],"raw_orcid":"https://orcid.org/0009-0004-3092-5319","affiliations":[{"raw_affiliation_string":"Institute of Radio Physics & Electronics, University of Calcutta, Kolkata, India","institution_ids":["https://openalex.org/I106542073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004894915","display_name":"Anurag Singh","orcid":"https://orcid.org/0000-0002-3639-2777"},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anurag Singh","raw_affiliation_strings":["Department of Electronics & Communication Engineering, International Institute of Information Technology, Naya Raipur, Chattisgarh, India"],"raw_orcid":"https://orcid.org/0000-0002-3639-2777","affiliations":[{"raw_affiliation_string":"Department of Electronics & Communication Engineering, International Institute of Information Technology, Naya Raipur, Chattisgarh, India","institution_ids":["https://openalex.org/I188963388"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066467382","display_name":"Ashish Kumar Bhandari","orcid":"https://orcid.org/0000-0001-9842-8125"},"institutions":[{"id":"https://openalex.org/I11793825","display_name":"National Institute of Technology Patna","ror":"https://ror.org/056wyhh33","country_code":"IN","type":"education","lineage":["https://openalex.org/I11793825","https://openalex.org/I4210152752"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Kumar Bhandari","raw_affiliation_strings":["Department of Electronics & Communication Engineering, National Institute of Technology Patna, Patna, India"],"raw_orcid":"https://orcid.org/0000-0001-9842-8125","affiliations":[{"raw_affiliation_string":"Department of Electronics & Communication Engineering, National Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I11793825"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0581,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88191434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"22","issue":"6","first_page":"3399","last_page":"3409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.49639999866485596,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.49639999866485596,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.3831999897956848,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11519","display_name":"Digital Mental Health Interventions","score":0.029400000348687172,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6520000100135803},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5461999773979187},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5121999979019165},{"id":"https://openalex.org/keywords/electroencephalography","display_name":"Electroencephalography","score":0.4853000044822693},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4544999897480011},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4235000014305115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41530001163482666},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.40939998626708984},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.3801000118255615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293000221252441},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6520000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5551000237464905},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5461999773979187},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4544999897480011},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39010000228881836},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2515000104904175}],"mesh":[{"descriptor_ui":"D000328","descriptor_name":"Adult","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000328","descriptor_name":"Adult","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000328","descriptor_name":"Adult","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003865","descriptor_name":"Depressive Disorder, Major","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D003865","descriptor_name":"Depressive Disorder, Major","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D003865","descriptor_name":"Major Depressive Disorder","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D004569","descriptor_name":"Electroencephalography","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D004569","descriptor_name":"Electroencephalography","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D004569","descriptor_name":"Electroencephalography","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbbio.2025.3626210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2025.3626210","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41144409","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41144409","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2112735526","https://openalex.org/W2479263883","https://openalex.org/W2513975684","https://openalex.org/W2530421149","https://openalex.org/W2885839206","https://openalex.org/W2998964460","https://openalex.org/W3094120200","https://openalex.org/W3097543391","https://openalex.org/W3105250175","https://openalex.org/W3110885177","https://openalex.org/W3119740068","https://openalex.org/W3126247264","https://openalex.org/W3164505422","https://openalex.org/W3181101419","https://openalex.org/W4205354408","https://openalex.org/W4224981562","https://openalex.org/W4281692204","https://openalex.org/W4284887989","https://openalex.org/W4285266524","https://openalex.org/W4286382578","https://openalex.org/W4287510307","https://openalex.org/W4290049250","https://openalex.org/W4295308158","https://openalex.org/W4302275554","https://openalex.org/W4312543714","https://openalex.org/W4313531753","https://openalex.org/W4324290675","https://openalex.org/W4382769645","https://openalex.org/W4387388453","https://openalex.org/W4387936925","https://openalex.org/W4388359375","https://openalex.org/W4392172671","https://openalex.org/W4392910576","https://openalex.org/W4401895152","https://openalex.org/W4403429813","https://openalex.org/W4404132887","https://openalex.org/W4404270187","https://openalex.org/W4404473968","https://openalex.org/W4409916903"],"related_works":[],"abstract_inverted_index":{"Major":[0],"Depressive":[1],"Disorder":[2],"(MDD)":[3],"is":[4,154,162],"a":[5,48,95,127,150,192],"debilitating":[6],"mental":[7],"health":[8],"condition":[9],"characterized":[10],"by":[11],"persistent":[12],"sadness,":[13],"anhedonia,":[14],"and":[15,40,55,66,112,158,183,189,213,223,245,251],"cognitive":[16],"impairments":[17],"that":[18],"significantly":[19],"disrupt":[20],"daily":[21],"functioning.":[22],"Accurate":[23],"diagnosis":[24],"remains":[25],"difficult":[26],"due":[27],"to":[28,116,133,156,173],"the":[29,36,75,106,139,147,159,165,171,201,206,228],"subjective":[30],"nature":[31],"of":[32,236],"clinical":[33,203,253],"assessments,":[34],"highlighting":[35],"need":[37],"for":[38,58,196],"objective":[39],"automated":[41],"diagnostic":[42],"tools.":[43],"Hence,":[44],"this":[45],"study":[46],"proposes":[47],"novel":[49,96],"multimodal":[50],"framework":[51,207],"integrating":[52],"electroencephalography":[53],"(EEG)":[54],"audio":[56,79,184],"signals":[57,63,80],"accurate":[59],"MDD":[60],"detection.":[61],"EEG":[62,182],"undergo":[64],"preprocessing":[65],"are":[67,81,91,123,186],"transformed":[68],"into":[69,83,94,191],"2D":[70,86],"time-frequency":[71],"(T-F)":[72],"representations":[73,87],"using":[74],"Superlet":[76],"Transform,":[77],"while":[78],"converted":[82],"Mel-spectrograms.":[84],"The":[85,101,119,219],"from":[88,146,181],"each":[89,117],"modality":[90],"independently":[92,180],"fed":[93,190],"Vision":[97],"Transformer":[98,129],"(ViT)":[99],"architecture.":[100],"proposed":[102,229],"ViT":[103],"first":[104],"slices":[105],"T-F":[107],"representation":[108,161],"along":[109],"frequency":[110],"bands":[111],"applies":[113],"positional":[114],"encoding":[115],"slice.":[118],"resulting":[120,241],"slice":[121],"embeddings":[122],"subsequently":[124],"processed":[125],"through":[126,164],"parallel":[128],"Encoder":[130,167],"(PE)":[131],"module":[132,141],"effectively":[134],"capture":[135,174],"temporal":[136],"dependencies.":[137],"After":[138],"PE":[140],"has":[142],"extracted":[143,179],"sufficient":[144],"information":[145],"embedded":[148],"slices,":[149],"learnable":[151],"class":[152],"token":[153],"appended":[155],"them,":[157],"combined":[160],"passed":[163],"Class":[166],"(CE)":[168],"module,":[169],"allowing":[170],"model":[172],"global":[175],"contextual":[176],"information.":[177],"Features":[178],"streams":[185],"then":[187],"fused":[188],"fully":[193],"connected":[194],"layer":[195],"final":[197],"classification.":[198],"Evaluation":[199],"on":[200],"MODMA":[202],"dataset":[204],"shows":[205],"achieves":[208],"98.86%":[209],"accuracy,":[210],"98.32%":[211],"F1-score,":[212],"0.9403":[214],"MCC,":[215],"surpassing":[216],"unimodal":[217],"baselines.":[218],"lightweight":[220],"feature":[221],"extraction":[222],"transformer-based":[224],"fusion":[225],"mechanisms":[226],"enable":[227],"architecture":[230],"deployable":[231],"in":[232,242],"an":[233],"edge-fog-cloud":[234],"Internet":[235],"Medical":[237],"Things":[238],"(IoMT)":[239],"system,":[240],"low-latency,":[243],"resource-efficient,":[244],"scalable":[246],"remote":[247],"diagnosis,":[248],"enhancing":[249],"accessibility":[250],"real-time":[252],"decision-making.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-29T00:00:00"}