{"id":"https://openalex.org/W7166872154","doi":"https://doi.org/10.18653/v1/2026.acl-long.58","title":"RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification","display_name":"RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166872154","doi":"https://doi.org/10.18653/v1/2026.acl-long.58"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.58","pdf_url":"https://aclanthology.org/2026.acl-long.58.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.58.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138360172","display_name":"Shakhrul Iman Siam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shakhrul Iman Siam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138390706","display_name":"Tiantian Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138359646","display_name":"Jiankun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiankun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139793749","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139826041","display_name":"Mi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93256743,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1316","last_page":"1330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.8371000289916992,"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"}},"topics":[{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.8371000289916992,"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/T12418","display_name":"Respiratory and Cough-Related Research","score":0.04560000076889992,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.027400000020861626,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/identification","display_name":"Identification (biology)","score":0.5958999991416931},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.43540000915527344},{"id":"https://openalex.org/keywords/disease","display_name":"Disease","score":0.31299999356269836},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.2434999942779541}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5958999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5151000022888184},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4325999915599823},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.40369999408721924},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2434999942779541},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.24210000038146973},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23829999566078186},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.22390000522136688}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.58","pdf_url":"https://aclanthology.org/2026.acl-long.58.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.58","pdf_url":"https://aclanthology.org/2026.acl-long.58.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.45738494396209717,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166872154.pdf","grobid_xml":"https://content.openalex.org/works/W7166872154.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Respiratory":[0],"diseases":[1,104],"remain":[2],"a":[3,50,117,126],"leading":[4],"cause":[5],"of":[6,139],"global":[7],"mortality,":[8],"where":[9],"timely":[10],"and":[11,20,42,62,68,93,113,125,146,202],"accurate":[12],"diagnosis":[13,145],"is":[14],"critical":[15],"to":[16,64,85,142],"improving":[17],"patient":[18,59],"outcomes":[19],"reducing":[21],"healthcare":[22],"burdens.While":[23],"prior":[24],"work":[25],"has":[26,187],"explored":[27],"audio-based":[28],"models":[29],"for":[30,78,200,204],"respiratory":[31,56,91,103,151],"disease":[32,69,152],"detection,":[33],"such":[34],"unimodal":[35],"approaches":[36],"often":[37],"suffer":[38],"from":[39],"limited":[40],"generalizability":[41],"diagnostic":[43,66],"precision.In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"RespiraMFM,":[49],"Multimodal":[51],"Foundation":[52],"Model":[53],"that":[54],"integrates":[55],"sounds":[57,92],"with":[58],"medical":[60],"history":[61],"symptoms":[63],"enhance":[65],"accuracy":[67],"detection":[70],"capabilities.We":[71],"introduce":[72],"an":[73],"effective":[74],"contrastive":[75],"alignment":[76],"strategy":[77],"audio-text":[79],"multimodal":[80],"integration,":[81],"allowing":[82],"the":[83,137,185,190],"model":[84],"learn":[86],"better":[87],"cross-modal":[88],"representations":[89],"between":[90],"corresponding":[94],"textual":[95],"clinical":[96,148],"information.We":[97],"evaluate":[98],"RespiraMFM":[99],"across":[100],"five":[101],"major":[102],"using":[105],"seven":[106],"real-world":[107],"datasets":[108],"in":[109,120,150],"both":[110],"supervised":[111,123],"fine-tuning":[112],"zero-shot":[114,130],"settings,":[115],"achieving":[116],"9.15%":[118],"improvement":[119],"AU-ROC":[121],"on":[122,129],"tasks":[124,131],"20.98%":[127],"gain":[128],"over":[132],"existing":[133],"baselines.These":[134],"findings":[135],"underscore":[136],"potential":[138],"our":[140],"framework":[141],"advance":[143],"early":[144],"improve":[147],"decision-making":[149],"management.{'sex':":[153],"'Male',":[154],"'age':":[155],"27,":[156],"'height':":[157],"173.3,'weight':":[158],"63.0,":[159],"'tb":[160],"prior':":[161],"'No',":[162,164],"'hemoptysis':":[163],"'heart":[165],"rate':":[166],"99,":[167],"'temperature':":[168],"37.2,":[169],"'weight":[170],"loss':":[171],"'Yes',":[172,176],"'smoke":[173],"lweek':":[174],"'No','fever':":[175],"'night":[177],"sweats':":[178],"'Yes','tb_status':":[179],"0,":[180],"'HIVstatus':":[181],"'Negative'}":[182],"Classify":[183],"whether":[184],"participant":[186],"COVID-19":[188],"given":[189],"following":[191],"information.The":[192],"2":[193],"classes":[194],"are:":[195],"healthy,":[196],"COVID19.Please":[197],"output":[198],"0":[199],"healthy":[201],"1":[203],"COVID19.":[205]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}