{"id":"https://openalex.org/W7160925193","doi":"https://doi.org/10.48550/arxiv.2605.08585","title":"PromptDx: Differentiable Prompt Tuning for Multimodal In-Context Alzheimer's Diagnosis","display_name":"PromptDx: Differentiable Prompt Tuning for Multimodal In-Context Alzheimer's Diagnosis","publication_year":2026,"publication_date":"2026-05-09","ids":{"openalex":"https://openalex.org/W7160925193","doi":"https://doi.org/10.48550/arxiv.2605.08585"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.08585","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08585","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.08585","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135940406","display_name":"Lujia Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Lujia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048252654","display_name":"Yihao Xia","orcid":"https://orcid.org/0000-0001-9327-1202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Yihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135932015","display_name":"Shuo Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136000923","display_name":"Jianwei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jianwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135923688","display_name":"Yonggang Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yonggang","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":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":0.4799000024795532,"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":0.4799000024795532,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.14270000159740448,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.08540000021457672,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.539900004863739},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4869999885559082},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4603999853134155},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45089998841285706},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.44209998846054077},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.3456999957561493},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.29910001158714294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6707000136375427},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5202999711036682},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.08585","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08585","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.08585","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08585","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Deep":[0],"learning":[1],"models":[2],"in":[3,200],"medical":[4],"imaging":[5],"typically":[6],"operate":[7],"as":[8,48,100,138],"parametric":[9,184],"memory,":[10],"diagnosing":[11],"patients":[12],"by":[13,35],"recalling":[14],"fixed":[15],"knowledge":[16],"learned":[17],"during":[18],"training.":[19],"This":[20],"contrasts":[21],"sharply":[22],"with":[23,61,108,128,221],"clinical":[24],"practice,":[25],"where":[26],"physicians":[27],"employ":[28],"analogical":[29],"reasoning":[30],"to":[31,72,80,198],"diagnose":[32],"new":[33],"cases":[34],"referencing":[36],"similar":[37],"records":[38],"from":[39],"past":[40],"exemplars.":[41],"While":[42],"In-Context":[43],"Learning":[44],"(ICL)":[45],"frameworks":[46],"such":[47],"Tabular":[49],"Prior-Fitted":[50],"Networks":[51],"(TabPFN)":[52],"offer":[53],"a":[54,91,97,115,123,135,139,228],"promising":[55],"diagnosis-by-reference":[56,93],"paradigm,":[57],"they":[58],"are":[59],"designed":[60],"tabular-specific":[62],"inductive":[63],"priors":[64],"and":[65,75,174,231],"rely":[66],"on":[67,163],"non-differentiable":[68,145],"preprocessing":[69],"pipelines,":[70],"leading":[71],"manifold":[73,205],"mismatch":[74],"gradient":[76],"fracture":[77],"when":[78],"applied":[79],"heterogeneous":[81],"multimodal":[82,109,153],"data.":[83],"To":[84],"address":[85],"these":[86],"limitations,":[87],"we":[88,147],"propose":[89],"PromptDx,":[90],"novel":[92],"framework":[94,216],"that":[95,121,179],"leverages":[96],"pre-trained":[98,130],"TabPFN":[99],"an":[101,149],"ICL":[102,131,157],"engine":[103],"while":[104],"enabling":[105],"seamless":[106],"integration":[107],"representations.":[110],"Our":[111],"core":[112],"contribution":[113],"is":[114],"Differentiable":[116],"Prompt":[117],"Tuning":[118],"(DPT)":[119],"mechanism":[120],"aligns":[122],"Masked":[124],"Multimodal":[125],"Modeling":[126],"module":[127],"the":[129,143,156,164,211],"engine.":[132],"By":[133],"training":[134],"lightweight":[136],"adapter":[137],"differentiable":[140],"surrogate":[141],"for":[142,235],"engine's":[144],"preprocessors,":[146],"enable":[148],"end-to-end":[150],"optimization":[151],"of":[152,213],"prompts":[154],"within":[155],"paradigm.":[158],"We":[159,208],"validate":[160,210],"our":[161,180,187,214,225],"method":[162,188,226],"Alzheimer's":[165,236],"Disease":[166,237],"Neuroimaging":[167],"Initiative":[168],"(ADNI)":[169],"dataset":[170],"using":[171,192],"3D":[172],"MRI":[173],"tabular":[175,219],"biomarkers.":[176],"Experiments":[177],"demonstrate":[178],"approach":[181],"outperforms":[182],"traditional":[183],"baselines.":[185],"Notably,":[186],"achieves":[189],"superior":[190],"performance":[191],"only":[193],"1%":[194],"context":[195],"samples":[196],"compared":[197],"30%":[199],"standard":[201],"ICL,":[202],"demonstrating":[203],"exceptional":[204],"condensation":[206],"ability.":[207],"further":[209],"generalizability":[212],"DPT":[215],"across":[217],"six":[218],"datasets":[220],"diverse":[222],"scales.":[223],"Overall,":[224],"offers":[227],"more":[229],"data-efficient":[230],"clinically":[232],"aligned":[233],"paradigm":[234],"diagnosis.":[238]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}