{"id":"https://openalex.org/W7124429059","doi":"https://doi.org/10.1101/2025.08.12.25333460","title":"PABformer: Multi-Channel Transformer-Based Physical Activity Representation Learning from Wearable Accelerometry for Prediction of Parkinson Disease","display_name":"PABformer: Multi-Channel Transformer-Based Physical Activity Representation Learning from Wearable Accelerometry for Prediction of Parkinson Disease","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W7124429059","doi":"https://doi.org/10.1101/2025.08.12.25333460"},"language":"en","primary_location":{"id":"doi:10.1101/2025.08.12.25333460","doi":"https://doi.org/10.1101/2025.08.12.25333460","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.08.12.25333460","pdf_url":null,"source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1101/2025.08.12.25333460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081523181","display_name":"Kai He","orcid":"https://orcid.org/0000-0003-3631-2172","observed_orcids":["https://orcid.org/0000-0003-3631-2172"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai He","raw_affiliation_strings":["University of Michigan"],"raw_orcid":"https://orcid.org/0000-0003-3631-2172","affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146853785","display_name":"Liuyi Fan","orcid":"https://orcid.org/0009-0003-8815-162X","observed_orcids":["https://orcid.org/0009-0003-8815-162X"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liuyi Fan","raw_affiliation_strings":["University of Michigan"],"raw_orcid":"https://orcid.org/0009-0003-8815-162X","affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118675736","display_name":"hanyu qian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanyu Qian","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132698340","display_name":"Chunyu Li","orcid":"https://orcid.org/0009-0001-3882-6866","observed_orcids":["https://orcid.org/0009-0001-3882-6866"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunyu Li","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100377087","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0001-5672-1411","observed_orcids":["https://orcid.org/0000-0001-5672-1411","https://orcid.org/0000-0002-3094-7735"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["University of Michigan"],"raw_orcid":"https://orcid.org/0000-0001-5672-1411","affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.7764000296592712,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.7764000296592712,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.044199999421834946,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10352","display_name":"Physical Activity and Health","score":0.03189999982714653,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"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/parkinson-s-disease","display_name":"Parkinson's disease","score":0.8970000147819519},{"id":"https://openalex.org/keywords/wearable-accelerometers","display_name":"wearable accelerometers","score":0.7490000128746033},{"id":"https://openalex.org/keywords/exercise","display_name":"physical activity","score":0.8119999766349792},{"id":"https://openalex.org/keywords/channel-separation","display_name":"channel separation","score":0.7559999823570251},{"id":"https://openalex.org/keywords/self-supervised-pretraining","display_name":"self-supervised pre-training","score":0.9570000171661377},{"id":"https://openalex.org/keywords/early-diagnosis","display_name":"early diagnosis","score":0.6710000038146973},{"id":"https://openalex.org/keywords/disease-risk-prediction","display_name":"disease risk prediction","score":0.5479999780654907},{"id":"https://openalex.org/keywords/grad-cam-interpretability","display_name":"Grad-CAM interpretability","score":0.7490000128746033},{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.6209999918937683},{"id":"https://openalex.org/keywords/uk-biobank","display_name":"UK Biobank","score":0.8059999942779541}],"concepts":[{"id":"https://openalex.org/C89805583","wikidata":"https://www.wikidata.org/wiki/Q192940","display_name":"Accelerometer","level":2,"score":0.9083999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6699000000953674},{"id":"https://openalex.org/C116567970","wikidata":"https://www.wikidata.org/wiki/Q864217","display_name":"Biobank","level":2,"score":0.656000018119812},{"id":"https://openalex.org/C2779363104","wikidata":"https://www.wikidata.org/wiki/Q17069079","display_name":"mHealth","level":3,"score":0.545199990272522},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5206999778747559},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5034000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4603999853134155},{"id":"https://openalex.org/C202645933","wikidata":"https://www.wikidata.org/wiki/Q4930","display_name":"eHealth","level":3,"score":0.42250001430511475},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4016999900341034},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C3020255362","wikidata":"https://www.wikidata.org/wiki/Q747883","display_name":"Physical activity","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.34540000557899475},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3296999931335449},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2025.08.12.25333460","doi":"https://doi.org/10.1101/2025.08.12.25333460","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.08.12.25333460","pdf_url":null,"source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/2025.08.12.25333460","doi":"https://doi.org/10.1101/2025.08.12.25333460","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.08.12.25333460","pdf_url":null,"source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"score":0.9537000060081482,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7199269662","https://openalex.org/W7172287600","https://openalex.org/W6912778976","https://openalex.org/W4386713180","https://openalex.org/W4382937268","https://openalex.org/W7204303601","https://openalex.org/W2986888469","https://openalex.org/W7171437206","https://openalex.org/W4313586098","https://openalex.org/W4413459197"],"abstract_inverted_index":{"Parkinson":[0],"disease":[1,231],"(PD)":[2],"is":[3],"a":[4,34,51,87,103,162],"prevalent":[5],"neurodegenerative":[6],"disorder":[7],"whose":[8],"early":[9,228],"diagnosis":[10],"and":[11,24,36,47,111,134,144,161,180,193,234],"prediction":[12,182],"remain":[13],"challenging":[14],"due":[15],"to":[16,72,106,115,226],"the":[17,25,128,190,217],"delayed":[18],"onset":[19],"of":[20,27,219],"overt":[21],"motor":[22],"symptoms":[23],"complexity":[26],"long-term":[28,93],"behavioral":[29,118,212],"changes.":[30],"Wearable":[31],"accelerometers":[32],"provide":[33],"scalable":[35],"non-invasive":[37],"approach":[38],"for":[39,54,92,138,222],"monitoring":[40],"physical":[41],"activity":[42,109],"(PA)":[43],"in":[44,77,127,176],"free-living":[45],"environments":[46],"have":[48],"emerged":[49],"as":[50,184],"promising":[52],"tool":[53],"PD":[55,142,146,178,229],"prediction.":[56,147],"However,":[57],"existing":[58],"accelerometer-based":[59],"methods":[60],"often":[61],"rely":[62],"on":[63],"coarse":[64],"summary":[65],"statistics":[66],"or":[67],"models":[68,221],"with":[69,210],"limited":[70],"ability":[71],"capture":[73],"long-range":[74],"temporal":[75],"dependencies":[76],"multi-day":[78],"accelerometer":[79,99,122,224],"recordings.":[80],"In":[81,198],"this":[82],"study,":[83],"we":[84,131],"propose":[85],"PABformer,":[86],"multi-channel":[88],"Transformer":[89,164],"framework":[90],"designed":[91],"PA":[94],"behavior":[95],"representation":[96],"learning":[97,155,159],"from":[98,124],"data.":[100],"PABformer":[101,133,150,172],"introduces":[102],"channel-separation":[104],"strategy":[105],"disentangle":[107],"heterogeneous":[108],"streams":[110],"leverages":[112],"self-supervised":[113],"pretraining":[114],"learn":[116],"generalized":[117],"representations.":[119],"Using":[120],"week-long":[121],"recordings":[123],"96,463":[125],"participants":[126],"UK":[129],"Biobank,":[130],"pretrained":[132],"subsequently":[135],"fine-tuned":[136],"it":[137],"demographic":[139],"attribute":[140],"inference,":[141],"diagnosis,":[143],"incident":[145],"We":[148],"compared":[149],"against":[151],"traditional":[152],"statistical,":[153],"machine":[154],"approaches,":[156],"recurrent":[157],"deep":[158],"models,":[160],"standard":[163],"without":[165],"channel":[166,207],"separation.":[167],"Experimental":[168],"results":[169],"demonstrated":[170],"that":[171],"achieved":[173],"superior":[174],"performance":[175],"both":[177],"classification":[179],"survival":[181],"tasks,":[183],"measured":[185],"by":[186,204],"precision-recall":[187],"area":[188],"under":[189],"curve":[191],"(PRAUC)":[192],"concordance":[194],"index":[195],"(C-index),":[196],"respectively.":[197],"addition,":[199],"Grad-CAM":[200],"analysis":[201],"improved":[202],"interpretability":[203],"identifying":[205],"salient":[206],"contributions":[208],"associated":[209],"PD-related":[211],"patterns.":[213],"These":[214],"findings":[215],"demonstrate":[216],"potential":[218],"foundation":[220],"wearable":[223],"data":[225],"advance":[227],"detection,":[230],"risk":[232],"prediction,":[233],"future":[235],"precision":[236],"health":[237],"applications.":[238]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-01-17T00:00:00"}