{"id":"https://openalex.org/W4414744618","doi":"https://doi.org/10.48550/arxiv.2509.16491","title":"FairTune: A Bias-Aware Fine-Tuning Framework Towards Fair Heart Rate Prediction from PPG","display_name":"FairTune: A Bias-Aware Fine-Tuning Framework Towards Fair Heart Rate Prediction from PPG","publication_year":2025,"publication_date":"2025-09-20","ids":{"openalex":"https://openalex.org/W4414744618","doi":"https://doi.org/10.48550/arxiv.2509.16491"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.16491","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.16491","pdf_url":"https://arxiv.org/pdf/2509.16491","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.16491","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093818804","display_name":"Lovely Yeswanth Panchumarthi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panchumarthi, Lovely Yeswanth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kataria, Saurabh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kataria, Saurabh","raw_affiliation_strings":["School of Nursing , Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Nursing , Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Yi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Yi","raw_affiliation_strings":["School of Nursing , Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Nursing , Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049689351","display_name":"Xiao Hu","orcid":"https://orcid.org/0000-0002-1295-3293","observed_orcids":["https://orcid.org/0000-0002-1295-3293"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]},{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu, Xiao","raw_affiliation_strings":["Computer Science , University of Oklahoma","School of Nursing , Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science , University of Oklahoma","institution_ids":["https://openalex.org/I8692664"]},{"raw_affiliation_string":"School of Nursing , Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059928810","display_name":"Alex Fedorov","orcid":"https://orcid.org/0000-0002-0350-9449","observed_orcids":["https://orcid.org/0000-0002-0350-9449"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fedorov, Alex","raw_affiliation_strings":["School of Nursing , Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Nursing , Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002390291","display_name":"Gloria Hyunjung Kwak","orcid":"https://orcid.org/0000-0002-0847-5073","observed_orcids":["https://orcid.org/0000-0002-0847-5073"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwak, Hyunjung Gloria","raw_affiliation_strings":["School of Nursing , Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Nursing , Emory University","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T11196","display_name":"Non-Invasive Vital Sign Monitoring","score":0.8130000233650208,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11196","display_name":"Non-Invasive Vital Sign Monitoring","score":0.8130000233650208,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.11599999666213989,"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"}},{"id":"https://openalex.org/T11021","display_name":"ECG Monitoring and Analysis","score":0.00570000009611249,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/heart-rate-prediction","display_name":"heart rate prediction","score":0.9829999804496765},{"id":"https://openalex.org/keywords/photoplethysmography","display_name":"photoplethysmography","score":0.9940000176429749},{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.7039999961853027},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8379999995231628},{"id":"https://openalex.org/keywords/demographic-fairness","display_name":"demographic fairness","score":0.8659999966621399},{"id":"https://openalex.org/keywords/gender-equity","display_name":"gender equity","score":0.6809999942779541},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.7879999876022339},{"id":"https://openalex.org/keywords/adversarial-debiasing","display_name":"adversarial debiasing","score":1.0},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.7910000085830688},{"id":"https://openalex.org/keywords/wearable-sensors","display_name":"wearable sensors","score":0.46299999952316284},{"id":"https://openalex.org/keywords/representation-analysis","display_name":"representation analysis","score":0.6909999847412109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034000158309937},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4902999997138977},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46459999680519104},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42750000953674316},{"id":"https://openalex.org/C116390426","wikidata":"https://www.wikidata.org/wiki/Q7187885","display_name":"Photoplethysmogram","level":3,"score":0.414000004529953},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C188154048","wikidata":"https://www.wikidata.org/wiki/Q6803609","display_name":"Mean absolute error","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.16491","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.16491","pdf_url":"https://arxiv.org/pdf/2509.16491","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.16491","doi":"https://doi.org/10.48550/arxiv.2509.16491","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.16491","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.16491","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.16491","pdf_url":"https://arxiv.org/pdf/2509.16491","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7390999794006348,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.504800021648407,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332622","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414744618.pdf","grobid_xml":"https://content.openalex.org/works/W4414744618.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2991497298","https://openalex.org/W3195577433","https://openalex.org/W3202467213","https://openalex.org/W4382492045","https://openalex.org/W4391212648","https://openalex.org/W4392427943","https://openalex.org/W4398192300","https://openalex.org/W4403370433"],"related_works":["https://openalex.org/W7163712500","https://openalex.org/W4414764702","https://openalex.org/W7163925619","https://openalex.org/W7213459365","https://openalex.org/W7221560220","https://openalex.org/W4410383903","https://openalex.org/W7140199293","https://openalex.org/W4404314147","https://openalex.org/W7148663359","https://openalex.org/W4404565447"],"abstract_inverted_index":{"Foundation":[0],"models":[1,25,102],"pretrained":[2,57],"on":[3,41,58,76,129],"physiological":[4,200],"data":[5,63],"such":[6],"as":[7,32,184],"photoplethysmography":[8],"(PPG)":[9],"signals":[10],"are":[11],"increasingly":[12],"used":[13],"to":[14,91,172],"improve":[15],"heart":[16],"rate":[17],"(HR)":[18],"prediction":[19,78],"across":[20,64],"diverse":[21],"settings.":[22],"Fine-tuning":[23],"these":[24],"for":[26,196],"local":[27],"deployment":[28,160,198],"is":[29,194],"often":[30],"seen":[31],"a":[33,53,115,185],"practical":[34],"and":[35,71,80,103,139,147,190],"scalable":[36],"strategy.":[37],"However,":[38],"its":[39],"impact":[40],"demographic":[42,174],"fairness":[43,97,151,180],"particularly":[44],"under":[45,104],"domain":[46],"shifts":[47],"remains":[48],"underexplored.":[49],"We":[50,143],"fine-tune":[51],"PPG-GPT":[52],"transformer-based":[54],"foundation":[55,201],"model":[56],"intensive":[59],"care":[60],"unit":[61],"(ICU)":[62],"three":[65,123],"heterogeneous":[66],"datasets":[67],"(ICU,":[68],"wearable,":[69],"smartphone)":[70],"systematically":[72],"evaluate":[73],"the":[74],"effects":[75],"HR":[77],"accuracy":[79],"gender":[81],"fairness.":[82],"While":[83],"fine-tuning":[84,117,189],"substantially":[85],"reduces":[86],"mean":[87],"absolute":[88],"error":[89],"(up":[90],"80%),":[92],"it":[93],"can":[94],"simultaneously":[95],"widen":[96],"gaps,":[98],"especially":[99],"in":[100,119],"larger":[101],"significant":[105],"distributional":[106],"characteristics":[107],"shifts.":[108],"To":[109],"address":[110],"this,":[111],"we":[112,121],"introduce":[113],"FairTune,":[114],"bias-aware":[116],"framework":[118],"which":[120],"benchmark":[122],"mitigation":[124,167,193],"strategies:":[125],"class":[126],"weighting":[127],"based":[128],"inverse":[130],"group":[131],"frequency":[132],"(IF),":[133],"Group":[134],"Distributionally":[135],"Robust":[136],"Optimization":[137],"(GroupDRO),":[138],"adversarial":[140],"debiasing":[141],"(ADV).":[142],"find":[144],"that":[145,166,179,191],"IF":[146],"GroupDRO":[148],"significantly":[149],"reduce":[150,173],"gaps":[152],"without":[153],"compromising":[154],"accuracy,":[155],"with":[156],"effectiveness":[157],"varying":[158],"by":[159],"domain.":[161],"Representation":[162],"analyses":[163],"further":[164],"reveal":[165],"techniques":[168],"reshape":[169],"internal":[170],"embeddings":[171],"clustering.":[175],"Our":[176],"findings":[177],"highlight":[178],"does":[181],"not":[182],"emerge":[183],"natural":[186],"byproduct":[187],"of":[188,199],"explicit":[192],"essential":[195],"equitable":[197],"models.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}