{"id":"https://openalex.org/W7225558304","doi":"https://doi.org/10.21203/rs.3.rs-11160715/v1","title":"Does Graph Attention Improve Weighted-Polling Classification on the Pima Indians Diabetes Dataset? A Nested Cross-Validation Comparison with Standard Models","display_name":"Does Graph Attention Improve Weighted-Polling Classification on the Pima Indians Diabetes Dataset? A Nested Cross-Validation Comparison with Standard Models","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225558304","doi":"https://doi.org/10.21203/rs.3.rs-11160715/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11160715/v1","doi":"https://doi.org/10.21203/rs.3.rs-11160715/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11160715/v1","pdf_url":"https://www.researchsquare.com/article/rs-11160715/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","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://www.researchsquare.com/article/rs-11160715/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022166861","display_name":"Farid Morsidi","orcid":"https://orcid.org/0000-0001-9812-1078","observed_orcids":["https://orcid.org/0000-0001-9812-1078"]},"institutions":[{"id":"https://openalex.org/I143923087","display_name":"Sultan Idris Education University","ror":"https://ror.org/005bjd415","country_code":"MY","type":"education","lineage":["https://openalex.org/I143923087"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Farid Morsidi","raw_affiliation_strings":["Universiti Pendidikan Sultan Idris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Pendidikan Sultan Idris","institution_ids":["https://openalex.org/I143923087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022166861"],"corresponding_institution_ids":["https://openalex.org/I143923087"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.5654000043869019,"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"}},"topics":[{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.5654000043869019,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.15389999747276306,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.07039999961853027,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph-attention-networks","display_name":"graph attention networks","score":0.9279999732971191},{"id":"https://openalex.org/keywords/gatv2","display_name":"GATv2","score":0.8799999952316284},{"id":"https://openalex.org/keywords/pima-indians-diabetes-dataset","display_name":"Pima Indians diabetes dataset","score":0.8019999861717224},{"id":"https://openalex.org/keywords/nested-cross-validation","display_name":"nested cross-validation","score":0.7400000095367432},{"id":"https://openalex.org/keywords/tabular-clinical-data","display_name":"tabular clinical data","score":0.6800000071525574},{"id":"https://openalex.org/keywords/classifier-comparison","display_name":"classifier comparison","score":0.628000020980835},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.7300000190734863}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C204854418","wikidata":"https://www.wikidata.org/wiki/Q1362921","display_name":"Polling","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131000280380249},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47510001063346863},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.412200003862381},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C161677786","wikidata":"https://www.wikidata.org/wiki/Q2478475","display_name":"Neighbourhood (mathematics)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C83282275","wikidata":"https://www.wikidata.org/wiki/Q7435350","display_name":"Scoring algorithm","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11160715/v1","doi":"https://doi.org/10.21203/rs.3.rs-11160715/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11160715/v1","pdf_url":"https://www.researchsquare.com/article/rs-11160715/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11160715/v1","doi":"https://doi.org/10.21203/rs.3.rs-11160715/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11160715/v1","pdf_url":"https://www.researchsquare.com/article/rs-11160715/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[{"score":0.6240000128746033,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225558304.pdf","grobid_xml":"https://content.openalex.org/works/W7225558304.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3032338640","https://openalex.org/W4399213099","https://openalex.org/W4401657615","https://openalex.org/W4411890052","https://openalex.org/W4415684655","https://openalex.org/W7133200336"],"related_works":["https://openalex.org/W2019353787","https://openalex.org/W2623213459","https://openalex.org/W7126235500","https://openalex.org/W7117143877","https://openalex.org/W3134529309","https://openalex.org/W2994682106","https://openalex.org/W4205437069","https://openalex.org/W7167508289","https://openalex.org/W7217265333","https://openalex.org/W4362560640"],"abstract_inverted_index":{"Abstract":[0],"Background:":[1],"It":[2],"is":[3],"not":[4,242,291],"known":[5],"whether":[6],"a":[7],"graph":[8,70,294],"attention":[9,77,295],"encoder":[10,75,238],"improvesweighted-polling":[11],"classification":[12],"of":[13,158,164,178,204,213,273],"small":[14],"clinical":[15],"tabular":[16],"datasets.":[17],"A":[18],"GATv2weighted-polling":[19],"classifier":[20,95,145],"developed":[21],"for":[22,138,211],"agricultural":[23],"morphology":[24],"data":[25],"was":[26,59,64,96],"thereforetested":[27],"on":[28,298],"the":[29,46,67,86,92,118,128,179,205,214,226,237],"Pima":[30],"Indians":[31],"Diabetes":[32],"Dataset":[33],"(768":[34],"instances,":[35],"8":[36],"features).":[37],"Itsfirst":[38],"evaluation":[39],"scored":[40],"nodes":[41],"whose":[42],"labels":[43],"had":[44,228],"trained":[45],"encoder.":[47],"Methods:":[48],"Nested":[49],"stratified":[50],"cross-validation":[51],"(10":[52],"outer":[53,90],"folds,":[54,57,91],"5":[55],"inner":[56,68,120],"threerepeats)":[58],"used,":[60],"and":[61,85,101,125,155,175,289],"every":[62],"hyperparameter":[63],"chosen":[65],"in":[66,117,268],"looponly:":[69],"neighbourhood":[71],"size,":[72],"edge":[73],"weighting,":[74],"width,":[76],"heads,dropout,":[78],"learning":[79],"rate,":[80],"weight":[81],"decay,":[82],"training":[83],"epochs":[84],"polling":[87,100,167,246],"configuration.On":[88],"identical":[89],"tuned":[93,116,143],"GATv2":[94,144,244],"comparedwith":[97],"raw-feature":[98,165,250,258],"weighted":[99,166,245],"five":[102,215],"standard":[103,182,216,254],"classifiers":[104],"(logistic":[105],"regression,RBF":[106],"support":[107],"vector":[108],"machine,":[109],"random":[110],"forest,":[111],"gradient":[112],"boosting,":[113],"k-nearestneighbours),":[114],"each":[115],"same":[119],"loop.":[121],"Accuracy,":[122],"macro-F1,":[123,150],"sensitivity,specificity":[124],"area":[126],"under":[127,239],"ROC":[129],"curve":[130],"(AUROC)":[131],"were":[132],"reported,":[133],"with":[134,208],"95%bootstrap":[135],"confidence":[136],"intervals":[137,209],"paired":[139],"differences.":[140],"Results:":[141],"The":[142,218],"reached":[146],"75.22%":[147],"accuracy,":[148],"71.90%":[149],"58.58%":[151],"sensitivity,":[152],"84.13%":[153],"specificity":[154],"an":[156],"AUROC":[157,196],"0.808.":[159],"Its":[160,195],"accuracydiffered":[161],"from":[162,176],"that":[163,177,203,293],"by":[168,187],"\u22120.13":[169],"points":[170,189,200,265,278],"(95%":[171,190],"CI\u22122.13":[172],"to":[173,193,198,224,257,275],"+1.87)":[174],"most":[180],"accurate":[181,248],"model,":[183],"logistic":[184],"regression":[185],"(76.74%),":[186],"\u22121.52":[188],"CI":[191],"\u22123.47":[192],"+0.39).":[194],"was1.4":[197],"2.5":[199],"lower":[201],"than":[202,249,253,262],"other":[206],"classifiers,":[207],"excludingzero":[210],"four":[212],"models.":[217],"original":[219],"protocol,":[220],"which":[221],"scorednodes":[222],"used":[223],"train":[225],"encoder,":[227],"given":[229],"79.01%":[230],"accuracy.":[231],"Conclusions:":[232],"On":[233],"this":[234,286],"dataset,":[235],"tuning":[236],"nested":[240],"cross-validationdid":[241],"make":[243],"more":[247],"weightedpolling":[251],"or":[252],"classifiers.":[255],"Relative":[256],"polling,":[259],"accuracydifferences":[260],"larger":[261],"about":[263,276],"2":[264],"are":[266,284],"excluded":[267],"either":[269],"direction,":[270],"but":[271],"abenefit":[272],"up":[274],"1.9":[277],"cannot":[279,296],"be":[280],"excluded.":[281],"These":[282],"findings":[283],"limitedto":[285],"single":[287],"dataset":[288],"do":[290],"show":[292],"help":[297],"otherclinical":[299],"data.":[300]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-11-09T00:00:00"}