{"id":"https://openalex.org/W7148774066","doi":"https://doi.org/10.48550/arxiv.2604.01841","title":"Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints","display_name":"Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148774066","doi":"https://doi.org/10.48550/arxiv.2604.01841"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.01841","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068475625","display_name":"Minh-Khoi Pham","orcid":"https://orcid.org/0000-0003-3211-9076"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pham, Minh-Khoi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129847218","display_name":"Thang-Long Nguyen Ho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ho, Thang-Long Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002706405","display_name":"Thao Thi Phuong Dao","orcid":"https://orcid.org/0000-0002-0109-1114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dao, Thao Thi Phuong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084358994","display_name":"Tai Tan","orcid":"https://orcid.org/0000-0001-6657-0872"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mai, Tai Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126787398","display_name":"Minh-Triet Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tran, Minh-Triet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132896904","display_name":"Marie E. Ward","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ward, Marie E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018591221","display_name":"\u00dana Geary","orcid":"https://orcid.org/0000-0001-7052-5863"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geary, Una","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087699589","display_name":"Rob Brennan","orcid":"https://orcid.org/0000-0001-8236-362X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brennan, Rob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001648625","display_name":"Nick McDonald","orcid":"https://orcid.org/0000-0002-1417-1148"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McDonald, Nick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038645621","display_name":"Martin Crane","orcid":"https://orcid.org/0000-0001-7598-3126"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Crane, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060543167","display_name":"Marija Bezbradica","orcid":"https://orcid.org/0000-0001-9366-5113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bezbradica, Marija","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5068475625"],"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":null,"issue":null,"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":0.9685999751091003,"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":0.9685999751091003,"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/T10028","display_name":"Topic Modeling","score":0.012400000356137753,"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/T10350","display_name":"Electronic Health Records Systems","score":0.003700000001117587,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.578499972820282},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5343999862670898},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5130000114440918},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5005000233650208},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5001000165939331},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4221000075340271},{"id":"https://openalex.org/keywords/electronic-health-record","display_name":"Electronic health record","score":0.4174000024795532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462999820709229},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.578499972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5691999793052673},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5134000182151794},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5115000009536743},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.4174000024795532},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3903999924659729},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.01841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Clinical":[0],"prediction":[1],"from":[2],"structured":[3],"electronic":[4],"health":[5],"records":[6],"(EHRs)":[7],"is":[8],"challenging":[9],"due":[10],"to":[11,102],"high":[12],"dimensionality,":[13,58],"heterogeneity,":[14],"class":[15],"imbalance,":[16,106],"and":[17,25,50,61,80,94,118],"distribution":[18],"shift.":[19],"While":[20],"tabular":[21,126],"in-context":[22,127],"learning":[23,93,128],"(TICL)":[24],"retrieval-augmented":[26],"methods":[27],"perform":[28],"well":[29],"on":[30],"generic":[31],"benchmarks,":[32],"their":[33],"behavior":[34],"in":[35,69,129],"clinical":[36,130],"settings":[37],"remains":[38],"unclear.":[39],"We":[40,83],"present":[41],"a":[42,86],"multi-cohort":[43],"EHR":[44],"benchmark":[45],"comparing":[46],"classical,":[47],"deep":[48],"tabular,":[49],"TICL":[51,65],"models":[52,66],"across":[53],"varying":[54],"data":[55,111],"scale,":[56],"feature":[57],"outcome":[59],"rarity,":[60],"cross-cohort":[62],"generalization.":[63],"PFN-based":[64],"are":[67],"sample-efficient":[68],"low-data":[70],"regimes":[71],"but":[72],"degrade":[73],"under":[74,104],"naive":[75],"distance-based":[76],"retrieval":[77,88,116],"as":[78,121],"heterogeneity":[79],"imbalance":[81],"increase.":[82],"propose":[84],"AWARE,":[85],"task-aligned":[87],"framework":[89],"using":[90],"supervised":[91],"embedding":[92],"lightweight":[95],"adapters.":[96],"AWARE":[97],"improves":[98],"AUPRC":[99],"by":[100],"up":[101],"12.2%":[103],"extreme":[105],"with":[107,110],"gains":[108],"increasing":[109],"complexity.":[112],"Our":[113],"results":[114],"identify":[115],"quality":[117],"retrieval-inference":[119],"alignment":[120],"key":[122],"bottlenecks":[123],"for":[124],"deploying":[125],"prediction.":[131]},"counts_by_year":[],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2026-04-04T00:00:00"}