{"id":"https://openalex.org/W7162540774","doi":"https://doi.org/10.48550/arxiv.2605.26589","title":"Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models for Childhood Anemia Prediction under Distribution Shift","display_name":"Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models for Childhood Anemia Prediction under Distribution Shift","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162540774","doi":"https://doi.org/10.48550/arxiv.2605.26589"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26589","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26589","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.26589","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068589144","display_name":"Yusuf Brima","orcid":"https://orcid.org/0000-0002-9975-8676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brima, Yusuf","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137087813","display_name":"Marcellin Atemkeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atemkeng, Marcellin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071326364","display_name":"Lansana Hassim Kallon","orcid":"https://orcid.org/0000-0002-3804-5218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kallon, Lansana Hassim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048087297","display_name":"David Niyukuri","orcid":"https://orcid.org/0000-0002-2112-4999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niyukuri, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070742303","display_name":"Antoine Vacavant","orcid":"https://orcid.org/0000-0001-9616-3282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vacavant, Antoine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136464936","display_name":"Samuel Saidu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saidu, Samuel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137152147","display_name":"Ding-Geng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ding-Geng","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/T10452","display_name":"Iron Metabolism and Disorders","score":0.9412999749183655,"subfield":{"id":"https://openalex.org/subfields/2720","display_name":"Hematology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10452","display_name":"Iron Metabolism and Disorders","score":0.9412999749183655,"subfield":{"id":"https://openalex.org/subfields/2720","display_name":"Hematology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10596","display_name":"Child Nutrition and Water Access","score":0.013899999670684338,"subfield":{"id":"https://openalex.org/subfields/2916","display_name":"Nutrition and Dietetics"},"field":{"id":"https://openalex.org/fields/29","display_name":"Nursing"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12735","display_name":"Blood donation and transfusion practices","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6315000057220459},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5076000094413757},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49300000071525574},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.47360000014305115},{"id":"https://openalex.org/keywords/brier-score","display_name":"Brier score","score":0.460099995136261},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4302000105381012}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6820999979972839},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6636999845504761},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C35405484","wikidata":"https://www.wikidata.org/wiki/Q4967066","display_name":"Brier score","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40299999713897705},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3361000120639801},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C2778248108","wikidata":"https://www.wikidata.org/wiki/Q5445","display_name":"Anemia","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.26339998841285706},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C187960798","wikidata":"https://www.wikidata.org/wiki/Q7631152","display_name":"Subgroup analysis","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26589","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26589","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.26589","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26589","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":"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":{"Childhood":[0],"anemia":[1,180],"affects":[2],"around":[3],"40%":[4],"of":[5],"children":[6],"aged":[7],"6-59":[8],"months":[9],"globally":[10],"and":[11,32,49,60,70,79,90,110,122,165,174,200],"arises":[12],"from":[13,39,130],"heterogeneous":[14],"factors,":[15],"limiting":[16],"model":[17,25,189],"generalizability.":[18],"We":[19,35,54],"evaluate":[20],"a":[21],"transformer-based":[22],"tabular":[23],"foundation":[24,203],"against":[26],"classical":[27,100],"supervised":[28],"methods":[29],"under":[30],"cross-country":[31],"data-scarce":[33,209],"settings.":[34,81],"used":[36],"DHS":[37],"data":[38],"16":[40],"countries":[41],"across":[42],"Africa,":[43],"Asia,":[44],"Latin":[45],"America,":[46],"the":[47,50,117],"Caucasus,":[48],"Middle":[51],"East":[52],"(n=68,856).":[53],"compared":[55],"Logistic":[56],"Regression,":[57],"XGBoost,":[58],"LightGBM,":[59],"TabPFN":[61,98,191],"v2.6.":[62],"Performance":[63,177],"was":[64,73,94,140,153],"assessed":[65],"using":[66,75,96],"AUC-ROC,":[67],"Brier":[68,119],"score,":[69],"ECE.":[71],"Generalization":[72],"evaluated":[74],"leave-one-country-out":[76],"(LOCO),":[77],"reverse-LOCO,":[78],"few-shot":[80],"Subgroup":[82,151],"analyses":[83],"included":[84],"sex,":[85],"age,":[86,163],"residence,":[87],"maternal":[88,175],"education,":[89],"wealth.":[91],"Feature":[92],"importance":[93],"estimated":[95],"SHAP.":[97],"outperformed":[99],"models":[101,204],"in":[102,178,194],"low-data":[103],"regimes":[104],"(<200":[105],"samples),":[106],"showing":[107],"higher":[108],"discrimination":[109,199],"better":[111],"calibration.":[112],"Across":[113],"countries,":[114],"it":[115],"achieved":[116],"lowest":[118],"score":[120],"(0.042)":[121],"ECE":[123],"(0.203).":[124],"Under":[125],"full-data":[126],"settings,":[127],"AUC-ROC":[128],"ranged":[129],"0.59-0.76":[131],"with":[132,155],"small":[133],"between-model":[134],"differences":[135],"($\\leq":[136],"0.05$).":[137],"LOCO":[138],"performance":[139,152],"stable":[141],"(0.58-0.69),":[142],"driven":[143,183],"by":[144,172,185],"country":[145],"context.":[146],"Reverse-LOCO":[147],"showed":[148],"asymmetric":[149],"transferability.":[150],"consistent":[154],"no":[156],"systematic":[157],"demographic":[158],"bias.":[159],"SHAP":[160],"identified":[161],"child":[162],"altitude,":[164],"height-for-age":[166],"z-score":[167],"as":[168,205],"dominant":[169],"predictors,":[170],"followed":[171],"wealth":[173],"education.":[176],"childhood":[179],"prediction":[181],"is":[182],"more":[184],"population":[186],"variation":[187],"than":[188],"choice.":[190],"provides":[192],"advantages":[193],"low-resource":[195],"settings":[196],"through":[197],"improved":[198],"calibration,":[201],"highlighting":[202],"promising":[206],"tools":[207],"for":[208],"global":[210],"health":[211],"prediction.":[212]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-28T00:00:00"}