{"id":"https://openalex.org/W4415799265","doi":"https://doi.org/10.1161/circ.152.suppl_3.4342997","title":"Abstract 4342997: Transformer-Based Survival Model Outperforms Traditional Methods for Cardiovascular Risk Prediction: Analysis of Two Million Annual Health Checkup Records in Japan","display_name":"Abstract 4342997: Transformer-Based Survival Model Outperforms Traditional Methods for Cardiovascular Risk Prediction: Analysis of Two Million Annual Health Checkup Records in Japan","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4415799265","doi":"https://doi.org/10.1161/circ.152.suppl_3.4342997"},"language":"en","primary_location":{"id":"doi:10.1161/circ.152.suppl_3.4342997","doi":"https://doi.org/10.1161/circ.152.suppl_3.4342997","is_oa":false,"landing_page_url":"https://doi.org/10.1161/circ.152.suppl_3.4342997","pdf_url":null,"source":{"id":"https://openalex.org/S116251202","display_name":"Circulation","issn_l":"0009-7322","issn":["0009-7322","1524-4539"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315671","host_organization_name":"Lippincott Williams & Wilkins","host_organization_lineage":["https://openalex.org/P4310315671","https://openalex.org/P4310318547"],"host_organization_lineage_names":["Lippincott Williams & Wilkins","Wolters Kluwer"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Circulation","raw_type":"journal-article"},"volume":null,"type":"conference-abstract","is_traditional":false,"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/A5049220778","display_name":"Shota Tsurimoto","orcid":"https://orcid.org/0009-0007-1685-9994","observed_orcids":["https://orcid.org/0009-0007-1685-9994"]},"institutions":[{"id":"https://openalex.org/I4210104330","display_name":"Kanazawa University Hospital","ror":"https://ror.org/00xsdn005","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210104330"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Tsurimoto","raw_affiliation_strings":["Kanazawa University Hospital, Kanazawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kanazawa University Hospital, Kanazawa, Japan","institution_ids":["https://openalex.org/I4210104330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041151982","display_name":"Yoshiki Nagata","orcid":"https://orcid.org/0000-0002-0217-697X","observed_orcids":["https://orcid.org/0000-0002-0217-697X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshiki Nagata","raw_affiliation_strings":["Hokuriku health service association, Laboratory of preventive medicine, Toyama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokuriku health service association, Laboratory of preventive medicine, Toyama, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035537632","display_name":"Akihiro Nomura","orcid":"https://orcid.org/0000-0001-6647-8240","observed_orcids":["https://orcid.org/0000-0001-6647-8240"]},"institutions":[{"id":"https://openalex.org/I4210104330","display_name":"Kanazawa University Hospital","ror":"https://ror.org/00xsdn005","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210104330"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Nomura","raw_affiliation_strings":["Kanazawa University Hospital, Kanazawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kanazawa University Hospital, Kanazawa, Japan","institution_ids":["https://openalex.org/I4210104330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050705557","display_name":"Masayuki Takamura","orcid":"https://orcid.org/0000-0002-1540-4417","observed_orcids":["https://orcid.org/0000-0002-1540-4417"]},"institutions":[{"id":"https://openalex.org/I4210104330","display_name":"Kanazawa University Hospital","ror":"https://ror.org/00xsdn005","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210104330"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Takamura","raw_affiliation_strings":["Kanazawa University Hospital, Kanazawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kanazawa University Hospital, Kanazawa, Japan","institution_ids":["https://openalex.org/I4210104330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"152","issue":"Suppl_3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.7095000147819519,"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"}},"topics":[{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.7095000147819519,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.24650000035762787,"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/T14212","display_name":"Health Promotion and Cardiovascular Prevention","score":0.03229999914765358,"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/cardiovascular-risk-prediction","display_name":"cardiovascular risk prediction","score":0.9380000233650208},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.671999990940094},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.3230000138282776},{"id":"https://openalex.org/keywords/antihypertensive-drugs","display_name":"antihypertensive drugs","score":0.7799999713897705},{"id":"https://openalex.org/keywords/electrocardiography","display_name":"electrocardiogram","score":0.8939999938011169},{"id":"https://openalex.org/keywords/weight-gain","display_name":"weight gain","score":0.7540000081062317},{"id":"https://openalex.org/keywords/framingham-risk-score","display_name":"Framingham risk score","score":0.8870000243186951},{"id":"https://openalex.org/keywords/external-validation","display_name":"external validation","score":0.5989999771118164},{"id":"https://openalex.org/keywords/toyama-prefecture","display_name":"Toyama Prefecture","score":0.7789999842643738},{"id":"https://openalex.org/keywords/kanazawa-city","display_name":"Kanazawa City","score":0.9739999771118164},{"id":"https://openalex.org/keywords/japan","display_name":"Japan","score":0.4189999997615814}],"concepts":[{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.8675000071525574},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.809499979019165},{"id":"https://openalex.org/C11783203","wikidata":"https://www.wikidata.org/wiki/Q5478027","display_name":"Framingham Risk Score","level":3,"score":0.5720000267028809},{"id":"https://openalex.org/C50382708","wikidata":"https://www.wikidata.org/wiki/Q223218","display_name":"Proportional hazards model","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C10515644","wikidata":"https://www.wikidata.org/wiki/Q543310","display_name":"Survival analysis","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.42660000920295715},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C111815664","wikidata":"https://www.wikidata.org/wiki/Q1440693","display_name":"Framingham Heart Study","level":4,"score":0.40790000557899475},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4072999954223633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36570000648498535},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3443000018596649},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C3018284874","wikidata":"https://www.wikidata.org/wiki/Q389735","display_name":"Cardiovascular health","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C207103383","wikidata":"https://www.wikidata.org/wiki/Q3930246","display_name":"Hazard ratio","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C3017977704","wikidata":"https://www.wikidata.org/wiki/Q18745135","display_name":"Health data","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.263700008392334},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1161/circ.152.suppl_3.4342997","doi":"https://doi.org/10.1161/circ.152.suppl_3.4342997","is_oa":false,"landing_page_url":"https://doi.org/10.1161/circ.152.suppl_3.4342997","pdf_url":null,"source":{"id":"https://openalex.org/S116251202","display_name":"Circulation","issn_l":"0009-7322","issn":["0009-7322","1524-4539"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315671","host_organization_name":"Lippincott Williams & Wilkins","host_organization_lineage":["https://openalex.org/P4310315671","https://openalex.org/P4310318547"],"host_organization_lineage_names":["Lippincott Williams & Wilkins","Wolters Kluwer"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Circulation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.98580002784729}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204268944","https://openalex.org/W7128060716","https://openalex.org/W7167801871","https://openalex.org/W4402857659","https://openalex.org/W7127935915","https://openalex.org/W7154457024","https://openalex.org/W7164555850","https://openalex.org/W4417510305","https://openalex.org/W4413174394","https://openalex.org/W7203911601"],"abstract_inverted_index":{"Background:":[0],"Cardiovascular":[1],"disease":[2],"(CVD)":[3],"is":[4],"a":[5,35,154],"global":[6],"health":[7,29,51,324],"concern.":[8],"Traditional":[9],"models":[10,108],"often":[11],"miss":[12],"nonlinear":[13],"dependencies":[14],"among":[15],"physiological":[16,273,317],"and":[17,103,123,141,153,216,241,272,285,308,322],"behavioral":[18,271],"factors.":[19],"Transformer-based":[20,277],"deep":[21],"learning":[22],"can":[23],"capture":[24],"complex":[25],"patterns":[26],"in":[27,193,266,282,301],"structured":[28],"data.":[30,82,106],"We":[31],"hypothesized":[32],"that":[33],"such":[34],"model,":[36],"trained":[37,99],"on":[38],"large-scale":[39],"check-up":[40,52],"records,":[41],"would":[42],"improve":[43],"long-term":[44,288],"CVD":[45,74,191,289],"risk":[46,290,303],"prediction.":[47,291],"Methods:":[48],"Using":[49],"annual":[50],"data":[53,88],"from":[54,89],"Toyama":[55,195],"Prefecture,":[56],"Japan":[57],"(n":[58,92],"=":[59,93],"100,056;":[60],"2010\u20132024),":[61],"we":[62,86],"excluded":[63],"individuals":[64],"with":[65],"baseline":[66],"CVD.":[67],"The":[68,95,197,276],"outcome":[69],"was":[70,98,131,146,168,261],"time":[71],"to":[72,183],"incident":[73],"over":[75],"10":[76],"years,":[77],"modeled":[78],"as":[79,243],"right-censored":[80],"survival":[81,113],"For":[83],"external":[84],"validation,":[85],"used":[87],"Kanazawa":[90,223],"City":[91],"79,756).":[94],"Transformer":[96,164,198],"model":[97,278,311],"using":[100,133,148],"anthropometric,":[101],"laboratory,":[102],"self-reported":[104],"lifestyle":[105],"Benchmark":[107],"included":[109],"Cox":[110],"regression,":[111],"XGBoost":[112],"embeddings,":[114],"multilayer":[115],"perceptron":[116],"(MLP),":[117],"the":[118,124,138,175,194,200,222,254,262,267,310],"Framingham":[119],"Risk":[120,126],"Score":[121,127],"(FRS),":[122],"Hisayama":[125],"(HRS).":[128],"Model":[129],"performance":[130,225,294],"evaluated":[132],"C-index,":[134],"time-dependent":[135],"area":[136],"under":[137],"curve":[139],"(AUC),":[140],"precision-recall":[142],"AUC":[143,212,230],"(PR-AUC).":[144],"Interpretability":[145],"assessed":[147],"SHapley":[149],"Additive":[150],"exPlanations":[151],"(SHAP)":[152],"Feature":[155],"Attention":[156,167],"Network":[157],"(FAN),":[158],"which":[159],"visualizes":[160],"directional":[161],"relationships":[162],"via":[163],"attention":[165,268],"weights.":[166],"computed":[169],"across":[170,295],"all":[171],"features,":[172],"but":[173],"only":[174],"top":[176],"12":[177],"ranked":[178],"by":[179],"SHAP":[180,234,307],"were":[181,189],"visualized":[182],"highlight":[184],"key":[185,244],"interactions.":[186],"Results:":[187],"There":[188],"4,113":[190],"events":[192],"cohort.":[196],"achieved":[199],"best":[201],"internal":[202],"performance:":[203],"C-index":[204],"0.796":[205],"(95%":[206],"confidence":[207],"interval":[208],"[CI]:":[209],"0.790\u20130.802),":[210],"10-year":[211],"0.821":[213],"(CI:":[214,219],"0.817\u20130.828),":[215],"PR-AUC":[217,232],"0.465":[218],"0.456\u20130.475).":[220],"In":[221],"cohort,":[224],"remained":[226],"strong":[227],"(C-index":[228],"0.743;":[229],"0.775;":[231],"0.504).":[233],"identified":[235],"age,":[236],"electrocardiogram":[237],"(ECG),":[238],"antihypertensive":[239],"medication,":[240],"sex":[242],"predictors.":[245],"FAN":[246],"highlighted":[247],"interpretable":[248],"relationships\u2014for":[249],"example,":[250],"weight":[251],"gain":[252],"shaped":[253],"model\u2019s":[255],"interpretation":[256],"of":[257],"age-related":[258],"risk.":[259],"Age":[260],"most":[263],"connected":[264],"node":[265],"network,":[269],"linking":[270],"features.":[274],"Conclusion:":[275],"outperformed":[279],"conventional":[280],"methods":[281],"both":[283],"discrimination":[284],"calibration":[286],"for":[287],"Its":[292],"consistent":[293],"distinct":[296],"populations":[297],"supports":[298],"its":[299],"utility":[300],"community-level":[302],"stratification.":[304],"By":[305],"combining":[306],"FAN,":[309],"reveals":[312],"how":[313],"modifiable":[314],"behaviors":[315],"influence":[316],"risk,":[318],"supporting":[319],"personalized":[320],"prevention":[321],"public":[323],"strategies.":[325]},"counts_by_year":[],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2025-11-03T00:00:00"}