{"id":"https://openalex.org/W7148490365","doi":"https://doi.org/10.1109/access.2026.3680428","title":"Toward a Device-Invariant and Bias-Resilient AI Framework for Acoustic Epidemiology","display_name":"Toward a Device-Invariant and Bias-Resilient AI Framework for Acoustic Epidemiology","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7148490365","doi":"https://doi.org/10.1109/access.2026.3680428"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3680428","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3680428","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3680428","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080438841","display_name":"Tabish Saeed","orcid":null},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tabish Saeed","raw_affiliation_strings":["Artificial Intelligence for Networks Research Center, School of Electrical and Computer Engineering, The University of Oklahoma, Tulsa, OK, USA"],"raw_orcid":"https://orcid.org/0009-0001-1325-9260","affiliations":[{"raw_affiliation_string":"Artificial Intelligence for Networks Research Center, School of Electrical and Computer Engineering, The University of Oklahoma, Tulsa, OK, USA","institution_ids":["https://openalex.org/I87208437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060732550","display_name":"Hifza Afzal","orcid":null},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hifza Afzal","raw_affiliation_strings":["Artificial Intelligence for Networks Research Center, School of Electrical and Computer Engineering, The University of Oklahoma, Tulsa, OK, USA"],"raw_orcid":"https://orcid.org/0009-0008-5582-3908","affiliations":[{"raw_affiliation_string":"Artificial Intelligence for Networks Research Center, School of Electrical and Computer Engineering, The University of Oklahoma, Tulsa, OK, USA","institution_ids":["https://openalex.org/I87208437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085604133","display_name":"Aneeqa Ijaz","orcid":"https://orcid.org/0000-0003-4359-4366"},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aneeqa Ijaz","raw_affiliation_strings":["Artificial Intelligence for Networks Research Center, School of Electrical and Computer Engineering, The University of Oklahoma, Tulsa, OK, USA"],"raw_orcid":"https://orcid.org/0000-0003-4359-4366","affiliations":[{"raw_affiliation_string":"Artificial Intelligence for Networks Research Center, School of Electrical and Computer Engineering, The University of Oklahoma, Tulsa, OK, USA","institution_ids":["https://openalex.org/I87208437"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101789165","display_name":"Ali Imran","orcid":"https://orcid.org/0000-0003-0564-6356"},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Imran","raw_affiliation_strings":["Artificial Intelligence for Networks Research Center, School of Electrical and Computer Engineering, The University of Oklahoma, Tulsa, OK, USA"],"raw_orcid":"https://orcid.org/0000-0003-0564-6356","affiliations":[{"raw_affiliation_string":"Artificial Intelligence for Networks Research Center, School of Electrical and Computer Engineering, The University of Oklahoma, Tulsa, OK, USA","institution_ids":["https://openalex.org/I87208437"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48862181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"57221","last_page":"57234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.15070000290870667,"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":0.15070000290870667,"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/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.10270000249147415,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.04610000178217888,"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/epidemiology","display_name":"Epidemiology","score":0.26159998774528503},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.218299999833107},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.21719999611377716},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.21130000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6265000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C107130276","wikidata":"https://www.wikidata.org/wiki/Q133805","display_name":"Epidemiology","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.218299999833107},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.21719999611377716},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2168000042438507},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.21130000054836273},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.20990000665187836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3680428","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3680428","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7bf3632a6dab4a51a9db22ae9982c833","is_oa":true,"landing_page_url":"https://doaj.org/article/7bf3632a6dab4a51a9db22ae9982c833","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 57221-57234 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3680428","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3680428","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-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":{"Acoustic":[0],"epidemiology,":[1,65],"the":[2,71,126,157,193,217,242],"use":[3],"of":[4],"sound-based":[5],"biomarkers":[6],"for":[7,19,63,142,268],"disease":[8,68],"detection,":[9],"has":[10],"shown":[11],"remarkable":[12],"potential":[13],"to":[14,24,115,177,202],"become":[15],"a":[16,54,59,77,85,89,107,178,185,265],"scalable":[17],"approach":[18],"population-level":[20],"health":[21],"surveillance.":[22],"However,":[23],"fully":[25],"realize":[26],"this":[27],"potential,":[28],"AI-based":[29],"diagnostic":[30],"frameworks":[31],"must":[32],"address":[33],"demographic":[34,98,198,261],"variation":[35],"and":[36,46,74,131,152,167,191,214,226,235,245,260],"recording":[37,150],"device":[38],"heterogeneity,":[39],"as":[40,70,76],"both":[41],"factors":[42],"can":[43],"limit":[44],"generalizability":[45],"real-world":[47,147],"utility.":[48],"To":[49,145],"explore":[50],"these":[51],"challenges":[52],"in":[53,149,188],"practical":[55,266],"setting,":[56],"we":[57,155],"develop":[58],"lightweight":[60],"AI":[61],"framework":[62,86,158,221],"acoustic":[64,270],"using":[66],"cough-based":[67],"screening":[69],"primary":[72],"modality":[73],"COVID-19":[75],"representative":[78],"case":[79],"study.":[80],"We":[81],"propose":[82],"Subgroup":[83],"VGGish\u2013XGBoost,":[84],"that":[87],"combines":[88],"cough-adapted":[90],"feature":[91,243],"extractor":[92,244],"with":[93,134],"multi-branch":[94],"classification":[95],"based":[96],"on":[97,110,159,182,211,216,223],"information.":[99],"Audio":[100],"features":[101],"are":[102],"extracted":[103],"by":[104,124,209],"fine-tuning":[105,241],"VGGish,":[106],"pretrained":[108],"network,":[109],"cough":[111,162],"versus":[112],"non-cough":[113],"sounds":[114],"improve":[116,253],"robustness":[117],"across":[118],"devices.":[119],"Demographic":[120],"bias-resilience":[121],"is":[122],"addressed":[123],"dividing":[125],"data":[127],"into":[128],"four":[129],"age":[130],"gender":[132],"subgroups,":[133],"separate":[135],"eXtreme":[136],"Gradient":[137],"Boosting":[138],"(XGBoost)":[139],"classifiers":[140,174,247],"trained":[141],"each":[143],"subgroup.":[144],"reflect":[146],"variability":[148],"devices":[151],"participant":[153,249],"demographics,":[154],"evaluate":[156],"three":[160],"different":[161],"datasets,":[163],"namely":[164],"COUGHVID,":[165],"Coswara,":[166],"AI4COVID-19,":[168,183],"through":[169],"two":[170,212],"experiments.":[171],"First,":[172],"subgroup-specific":[173],"were":[175],"compared":[176],"single":[179],"global":[180],"model":[181],"yielding":[184],"1.5%":[186],"increase":[187],"overall":[189,254],"accuracy":[190,194,229],"narrowing":[192],"gap,":[195],"\u0394Accuracy,":[196],"between":[197],"subgroups":[199],"from":[200],"20.9%":[201],"9.6%.":[203],"Second,":[204],"cross-dataset":[205],"generalization":[206],"was":[207],"assessed":[208],"training":[210],"datasets":[213],"testing":[215],"third.":[218],"The":[219],"proposed":[220],"achieved,":[222],"average,":[224],"10.3%":[225],"9.1%":[227],"higher":[228],"than":[230],"state-of-the-art":[231],"architectures":[232],"like":[233],"ResNet-101":[234],"MobileNetV2,":[236],"respectively.":[237],"These":[238],"results":[239],"demonstrate":[240],"designing":[246],"around":[248],"characteristics":[250],"not":[251],"only":[252],"accuracy,":[255],"but":[256],"also":[257],"enhance":[258],"device-invariance":[259],"bias-resilience;":[262],"thus,":[263],"providing":[264],"foundation":[267],"AI-enabled":[269],"epidemiology.":[271]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-03T00:00:00"}