{"id":"https://openalex.org/W7126068908","doi":"https://doi.org/10.1109/bibm66473.2025.11356716","title":"From Voice to Diagnosis: A Hybrid Approach to Multi-Label Disease Classification with Uncertainty Awareness","display_name":"From Voice to Diagnosis: A Hybrid Approach to Multi-Label Disease Classification with Uncertainty Awareness","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126068908","doi":"https://doi.org/10.1109/bibm66473.2025.11356716"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5121237668","display_name":"Weixin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weixin Liu","raw_affiliation_strings":["Vanderbilt University,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Nashville,TN,USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013062831","display_name":"Bowen Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowen Qu","raw_affiliation_strings":["Vanderbilt University,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Nashville,TN,USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124222723","display_name":"Matthew E Pontell","orcid":null},"institutions":[{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew E Pontell","raw_affiliation_strings":["Vanderbilt University Medical Center,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University Medical Center,Nashville,TN,USA","institution_ids":["https://openalex.org/I901861585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003384228","display_name":"Maria Powell","orcid":"https://orcid.org/0000-0002-6643-8991"},"institutions":[{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maria E Powell","raw_affiliation_strings":["Vanderbilt University Medical Center,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University Medical Center,Nashville,TN,USA","institution_ids":["https://openalex.org/I901861585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090647314","display_name":"Bradley Malin","orcid":"https://orcid.org/0000-0003-3040-5175"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bradley A Malin","raw_affiliation_strings":["Vanderbilt University,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Nashville,TN,USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079247989","display_name":"Zhijun Yin","orcid":"https://orcid.org/0000-0002-3075-1337"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhijun Yin","raw_affiliation_strings":["Vanderbilt University,Nashville,TN,USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Nashville,TN,USA","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5121237668"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74679472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4776","last_page":"4783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.861299991607666,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.861299991607666,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"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/T12418","display_name":"Respiratory and Cough-Related Research","score":0.03840000182390213,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory 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/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.033900000154972076,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7330999970436096},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5683000087738037},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5401999950408936},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49639999866485596},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.45100000500679016},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4047999978065491},{"id":"https://openalex.org/keywords/multiclass-classification","display_name":"Multiclass classification","score":0.3847000002861023},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3788999915122986}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7330999970436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.718999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087000012397766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5965999960899353},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C123860398","wikidata":"https://www.wikidata.org/wiki/Q6934605","display_name":"Multiclass classification","level":3,"score":0.3847000002861023},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3788999915122986},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7377928495407104,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2161648413","https://openalex.org/W2194775991","https://openalex.org/W2790046776","https://openalex.org/W2963351448","https://openalex.org/W2964059111","https://openalex.org/W3091468319","https://openalex.org/W3115596824","https://openalex.org/W4224885307","https://openalex.org/W4288467237","https://openalex.org/W4289516314","https://openalex.org/W4311496987","https://openalex.org/W4361216148","https://openalex.org/W4384469206","https://openalex.org/W4386325834","https://openalex.org/W4392035505","https://openalex.org/W4403330073","https://openalex.org/W4404277329","https://openalex.org/W4408930482","https://openalex.org/W4409733622"],"related_works":[],"abstract_inverted_index":{"The":[0],"human":[1],"voice":[2,37,334],"encodes":[3],"a":[4,32,54,77,97,106,128,140,261,267,312,317,322],"wealth":[5],"of":[6,45,72,207,213,226],"acoustic":[7,121],"biomarkers":[8],"linked":[9],"to":[10,18,38,80,178,243,326],"various":[11],"health":[12],"conditions,":[13],"including":[14],"but":[15],"not":[16],"limited":[17],"neurological,":[19],"mood,":[20],"respiratory,":[21],"and":[22,42,68,85,95,149,158,175,193,220,247,263,274],"laryngeal":[23],"disorders.":[24],"Recent":[25],"advancements":[26],"in":[27,200],"artificial":[28],"intelligence":[29],"(AI)":[30],"offer":[31],"promising":[33],"solution":[34],"for":[35,100,296,316],"leveraging":[36],"perform":[39],"noninvasive,":[40],"cost-effective,":[41],"scalable":[43],"screening":[44],"health-related":[46],"conditions.":[47],"However,":[48],"classifying":[49],"comorbid":[50],"clinical":[51,87],"conditions":[52],"presents":[53,311],"significant":[55,269],"multi-label":[56,102],"classification":[57,104,222],"challenge,":[58],"which":[59],"is":[60],"further":[61],"complicated":[62],"by":[63],"class":[64],"imbalance,":[65],"feature":[66],"noise,":[67],"the":[69,111,133,186,197,204,233,293,332],"\u201cblack-box\u201d":[70],"nature":[71],"modern":[73],"deep":[74,125],"learning":[75],"models,":[76],"critical":[78],"barrier":[79],"model":[81,136,199,231,272,329],"interpretability,":[82],"error":[83,276],"analysis,":[84],"potential":[86],"translation.":[88],"To":[89,131],"address":[90],"these":[91],"challenges,":[92],"we":[93,138,163],"introduce":[94],"evaluate":[96],"two-stage":[98,188,240],"framework":[99],"voice-based,":[101],"disease":[103],"on":[105],"newly":[107],"curated":[108],"dataset":[109],"from":[110,127],"NIH":[112],"Bridge2AI":[113,333],"initiative.":[114],"This":[115],"hybrid":[116],"approach":[117,241],"fuses":[118],"theory-driven,":[119],"handcrafted":[120],"features":[122,126],"with":[123,145,190,257,292],"data-driven":[124],"pre-trained":[129],"ResNet-18.":[130],"identify":[132],"most":[134],"effective":[135,264],"configuration,":[137],"enhance":[139],"Feed-Forward":[141],"Neural":[142],"Network":[143],"(FFNN)":[144],"an":[146,165,229],"attention":[147],"mechanism":[148],"Focal":[150,191],"Loss,":[151],"systematically":[152],"comparing":[153],"it":[154],"against":[155],"traditional":[156],"classifiers":[157],"end-to-end":[159,230],"fine-tuning":[160],"benchmarks.":[161],"Finally,":[162],"incorporate":[164],"uncertainty":[166,273],"quantification":[167],"(UQ)":[168],"layer":[169],"using":[170,331],"Monte":[171],"Carlo":[172],"(MC)":[173],"Dropout":[174,256],"Deep":[176],"Ensembles":[177],"assess":[179],"prediction":[180,275],"reliability.":[181],"Our":[182],"results":[183],"show":[184],"that":[185],"proposed":[187],"FFNN":[189],"Loss":[192],"Attention":[194],"emerges":[195],"as":[196,260],"best-performing":[198],"our":[201,239,251],"evaluation,":[202],"delivering":[203],"best":[205],"balance":[206],"high":[208],"discriminative":[209],"power":[210],"(Macro":[211,224],"AUC":[212],"<tex":[214,278,286],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[215,279,287,300],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{0.":[216],"8":[217,284,305],"1":[218],"0}$</tex>)":[219],"robust":[221,313],"accuracy":[223],"F1":[225,236],"0.610).":[227],"While":[228],"achieved":[232],"highest":[234],"Macro":[235],"score":[237],"(0.638),":[238],"proved":[242],"be":[244],"more":[245],"reliable":[246],"computationally":[248],"efficient.":[249],"Furthermore,":[250],"UQ":[252],"analysis":[253],"identified":[254],"MC":[255],"Predictive":[258],"Entropy":[259],"practical":[262],"method,":[265],"revealing":[266],"statistically":[268],"correlation":[270],"between":[271],"(overall":[277],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{r}":[280,301],"\\boldsymbol{=}":[281,302],"\\mathbf{0.":[282,303],"2":[283],"0}$</tex>,":[285],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{p}&lt;\\mathbf{0.":[288],"0":[289,290],"1}$</tex>),":[291],"strongest":[294],"link":[295],"Voice":[297],"Disorders":[298],"(<tex":[299],"3":[304],"0}$</tex>).":[306],"In":[307],"summary,":[308],"this":[309],"study":[310],"technical":[314],"blueprint":[315],"voice-based":[318],"AI":[319],"system,":[320],"establishing":[321],"strong":[323],"performance":[324],"benchmark":[325],"guide":[327],"future":[328],"development":[330],"dataset.":[335]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-30T00:00:00"}