{"id":"https://openalex.org/W7204083541","doi":"https://doi.org/10.2196/preprints.109774","title":"Classical Machine Learning Versus a Feature-Token Transformer for Diphtheria and Dengue Surveillance in Yemen: Repeated-Seed Nested and Temporal Validation Study (Preprint)","display_name":"Classical Machine Learning Versus a Feature-Token Transformer for Diphtheria and Dengue Surveillance in Yemen: Repeated-Seed Nested and Temporal Validation Study (Preprint)","publication_year":2026,"publication_date":"2026-08-17","ids":{"openalex":"https://openalex.org/W7204083541","doi":"https://doi.org/10.2196/preprints.109774"},"language":"en","primary_location":{"id":"doi:10.2196/preprints.109774","doi":"https://doi.org/10.2196/preprints.109774","is_oa":false,"landing_page_url":"https://doi.org/10.2196/preprints.109774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"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/A5075280202","display_name":"Bilal Abdualgalil","orcid":"https://orcid.org/0000-0002-8293-037X","observed_orcids":["https://orcid.org/0000-0002-8293-037X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bilal Abdualgalil","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8293-037X","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088114683","display_name":"Ansam Wadia Alshameri","orcid":"https://orcid.org/0000-0002-1460-6842","observed_orcids":["https://orcid.org/0000-0002-1460-6842","https://orcid.org/0000-0002-9047-0748"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ansam Wadia Alshameri","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9047-0748","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042655679","display_name":"Amgad S.D. Khaled","orcid":"https://orcid.org/0000-0003-0040-3849","observed_orcids":["https://orcid.org/0000-0003-0040-3849"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amgad S D Khaled","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0040-3849","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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.5360999703407288,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.5360999703407288,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.1996999979019165,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.07729999721050262,"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/diphtheria-surveillance","display_name":"diphtheria surveillance","score":0.9399999976158142},{"id":"https://openalex.org/keywords/dengue-surveillance","display_name":"dengue surveillance","score":0.9909999966621399},{"id":"https://openalex.org/keywords/classical-machine-learning","display_name":"classical machine learning","score":0.5680000185966492},{"id":"https://openalex.org/keywords/temporal-validation","display_name":"temporal validation","score":0.6150000095367432},{"id":"https://openalex.org/keywords/temporal-leakage","display_name":"temporal leakage","score":0.6340000033378601},{"id":"https://openalex.org/keywords/nested-cross-validation","display_name":"nested cross-validation","score":0.5199999809265137},{"id":"https://openalex.org/keywords/model-comparison","display_name":"model comparison","score":0.3490000069141388},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"ensemble forecasting","score":0.4300000071525574},{"id":"https://openalex.org/keywords/decision-curve-analysis","display_name":"decision curve analysis","score":0.5600000023841858},{"id":"https://openalex.org/keywords/calibration","display_name":"calibration","score":0.5490000247955322},{"id":"https://openalex.org/keywords/selection-bias","display_name":"selection bias","score":0.6050000190734863},{"id":"https://openalex.org/keywords/yemen","display_name":"Yemen","score":0.328000009059906},{"id":"https://openalex.org/keywords/disease-notification-data","display_name":"disease notification data","score":0.328000009059906},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.9800000190734863},{"id":"https://openalex.org/keywords/neural-network-classifier","display_name":"neural network classifier","score":0.38999998569488525},{"id":"https://openalex.org/keywords/dengue-serology","display_name":"dengue serology","score":0.6669999957084656}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6699000000953674},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6370999813079834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6150000095367432},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5002999901771545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4271000027656555},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C533803919","wikidata":"https://www.wikidata.org/wiki/Q30953","display_name":"Dengue fever","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C2780572238","wikidata":"https://www.wikidata.org/wiki/Q134649","display_name":"Diphtheria","level":3,"score":0.3752000033855438},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C186282968","wikidata":"https://www.wikidata.org/wiki/Q1434261","display_name":"McNemar's test","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.26260000467300415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2196/preprints.109774","doi":"https://doi.org/10.2196/preprints.109774","is_oa":false,"landing_page_url":"https://doi.org/10.2196/preprints.109774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.9391000270843506}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2151591509","https://openalex.org/W2295598076","https://openalex.org/W2996480032","https://openalex.org/W3172701880","https://openalex.org/W3174086521","https://openalex.org/W3202428668","https://openalex.org/W4220881383","https://openalex.org/W4385576721","https://openalex.org/W4394908947","https://openalex.org/W4396541948","https://openalex.org/W4399540278","https://openalex.org/W7133186244"],"related_works":["https://openalex.org/W7156748825","https://openalex.org/W3101689426","https://openalex.org/W7213166053","https://openalex.org/W4225165959","https://openalex.org/W4315632054","https://openalex.org/W7223561811","https://openalex.org/W7204850911","https://openalex.org/W7125486994","https://openalex.org/W4220881383","https://openalex.org/W4206827170"],"abstract_inverted_index":{"BACKGROUND":[0],"Comparative":[1],"evaluation":[2],"of":[3,84,346],"machine-learning":[4],"models":[5,166,328,369],"for":[6,42,130,163,357],"health":[7],"surveillance":[8,46],"data":[9,47],"can":[10],"be":[11],"distorted":[12],"by":[13,246],"asymmetric":[14],"random-seed":[15],"evaluation,":[16,53],"single":[17],"holdout":[18],"splits,":[19],"weak":[20],"hyperparameter":[21],"tuning,":[22],"inappropriate":[23],"missing-data":[24],"handling,":[25],"duplicate":[26],"predictor":[27,149],"profiles,":[28],"and":[29,38,44,62,97,102,133,187,195,219,253,282,303,401,418],"temporal":[30,56,140,165,334,374],"leakage.":[31],"OBJECTIVE":[32],"We":[33],"compared":[34,351],"11":[35],"classical,":[36],"neural,":[37],"feature-token":[39,255,378],"Transformer":[40,256,379],"classifiers":[41],"diphtheria":[43,69,295,403],"dengue":[45,391],"from":[48,79,112,121,126,156,199,226,311],"Yemen":[49],"using":[50,93,169],"symmetric":[51],"repeated-seed":[52],"group-aware":[54],"validation,":[55,417],"testing,":[57],"calibration":[58,284],"assessment,":[59],"decision-curve":[60,188],"analysis,":[61],"a":[63,80,138,212,283,342],"selection-bias":[64],"audit.":[65],"METHODS":[66],":":[67],"The":[68,261,294,377],"analytic":[70],"cohort":[71],"included":[72],"566":[73],"records":[74,111],"with":[75,116,146,341,352,410],"definitive":[76],"culture":[77,412],"results":[78],"source":[81],"line":[82],"list":[83],"2,035":[85],"suspected":[86],"or":[87],"notified":[88],"cases.":[89],"Models":[90],"were":[91,119,128,167,204,223,370],"evaluated":[92],"identical":[94],"5-fold":[95],"outer":[96],"3-fold":[98],"inner":[99],"StratifiedGroupKFold":[100],"cross-validation":[101,171],"the":[103,122,157,177,192,200,207,236,254,273,277,291,318,333,358,360,383,397,402],"same":[104],"5":[105,201],"random":[106,247],"seeds.":[107],"For":[108,191,231,306],"dengue,":[109,307],"118":[110],"27":[113],"predictor-identical":[114],"groups":[115],"conflicting":[117],"labels":[118],"excluded":[120,155,304],"primary":[123,159,178,193],"analysis.":[124],"Data":[125],"2017-2018":[127,173],"used":[129],"development":[131,153,314],"(n=3,672),":[132],"2019":[134,144,320],"was":[135,154,176,265,324,363],"reserved":[136],"as":[137],"locked":[139],"test":[141,160],"set.":[142],"One":[143],"record":[145],"an":[147],"exact":[148],"profile":[150],"observed":[151],"during":[152,313],"strict":[158,319],"(n=2,314).":[161],"Hyperparameters":[162],"final":[164],"selected":[168],"group":[170],"within":[172],"only.":[174],"Macro-F1":[175,240,331,345],"metric.":[179],"Additional":[180],"measures":[181],"assessed":[182],"classification":[183],"performance,":[184],"discrimination,":[185],"calibration,":[186],"net":[189],"benefit.":[190],"confidence-interval":[194],"paired-comparison":[196],"analyses,":[197],"probabilities":[198],"seed-specific":[202],"fits":[203],"averaged":[205],"at":[206],"observation":[208],"level":[209],"to":[210,287,315,396,408],"form":[211],"5-model":[213],"probability":[214],"ensemble.":[215],"Group-bootstrap":[216],"95%":[217,242,250,258],"CIs":[218],"paired":[220,361],"group-bootstrap":[221],"differences":[222,300],"then":[224],"calculated":[225],"these":[227],"ensemble":[228,239,344],"predictions.":[229],"RESULTS":[230],"diphtheria,":[232],"Deep":[233,262],"MLP":[234],"had":[235,272,329],"highest":[237,274],"5-seed":[238,343],"(0.6372,":[241],"CI":[243,251,259,268,349,355,366],"0.5962-0.6757),":[244],"followed":[245],"forest":[248,271],"(0.6263,":[249],"0.5879-0.6665)":[252],"(0.5897,":[257],"0.5468-0.6322).":[260],"MLP-minus-Transformer":[263],"difference":[264,362],"0.0475":[266],"(95%":[267,348,354,365],"0.0078-0.0871).":[269],"Random":[270],"ROC-AUC":[275],"(0.6718),":[276],"lowest":[278],"Brier":[279],"score":[280],"(0.2278),":[281],"slope":[285],"closest":[286],"1":[288],"(0.8499)":[289],"among":[290],"leading":[292],"models.":[293],"selection":[296,404],"audit":[297,405],"showed":[298],"substantial":[299],"between":[301],"retained":[302],"records.":[305],"positive":[308],"prevalence":[309],"increased":[310],"46.8%":[312],"79.8%":[316],"in":[317,339],"test.":[321,335],"Internal":[322],"performance":[323,392],"high,":[325],"but":[326],"all":[327],"lower":[330],"on":[332,386],"XGBoost":[336],"performed":[337],"best":[338],"2019,":[340],"0.5109":[347],"0.4886-0.5328),":[350],"0.4421":[353],"0.4204-0.4639)":[356],"Transformer;":[359],"0.0688":[364],"0.0523-0.0852).":[367],"Both":[368],"poorly":[371],"calibrated":[372],"after":[373],"shift.":[375],"CONCLUSIONS":[376],"did":[380,393],"not":[381,394],"outperform":[382],"strongest":[384],"comparator":[385],"either":[387],"task.":[388],"Strong":[389],"internal":[390],"translate":[395],"subsequent":[398],"calendar":[399],"period,":[400],"limits":[406],"inference":[407],"cases":[409],"classifiable":[411],"results.":[413],"Prospective":[414],"recalibration,":[415],"external":[416],"setting-specific":[419],"utility":[420],"assessment":[421],"are":[422],"required":[423],"before":[424],"deployment.":[425],"CLINICALTRIAL":[426],"na":[427]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-08-25T00:00:00"}