{"id":"https://openalex.org/W7202367291","doi":"https://doi.org/10.54660/ijmbhr.2026.7.3.168-174","title":"An Interpretable XGBoost Model for Diabetes Prediction: Nested Cross-Validation, Calibration, and SHAP Analysis","display_name":"An Interpretable XGBoost Model for Diabetes Prediction: Nested Cross-Validation, Calibration, and SHAP Analysis","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7202367291","doi":"https://doi.org/10.54660/ijmbhr.2026.7.3.168-174"},"language":"en","primary_location":{"id":"doi:10.54660/ijmbhr.2026.7.3.168-174","doi":"https://doi.org/10.54660/ijmbhr.2026.7.3.168-174","is_oa":true,"landing_page_url":"https://doi.org/10.54660/ijmbhr.2026.7.3.168-174","pdf_url":null,"source":{"id":"https://openalex.org/S4210185971","display_name":"International Journal of Medical and All Body Health Research","issn_l":"2582-8940","issn":["2582-8940"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Medical and All Body Health Research","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.54660/ijmbhr.2026.7.3.168-174","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078259919","display_name":"Zeynep K\u00fc\u00e7\u00fckak\u00e7al\u0131","orcid":"https://orcid.org/0000-0001-7956-9272","observed_orcids":["https://orcid.org/0000-0001-7956-9272"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeynep Kucukakcali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067186768","display_name":"\u0130pek Bal\u0131k\u00e7\u0131 \u00c7i\u00e7ek","orcid":"https://orcid.org/0000-0002-3805-9214","observed_orcids":["https://orcid.org/0000-0002-3805-9214"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ipek Balikci Cicek","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59725423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"3","first_page":"168","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9901999831199646,"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":0.9901999831199646,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.004000000189989805,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.00139999995008111,"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/diabetes-prediction","display_name":"diabetes prediction","score":0.9300000071525574},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.9800000190734863},{"id":"https://openalex.org/keywords/nested-cross-validation","display_name":"nested cross-validation","score":0.8420000076293945},{"id":"https://openalex.org/keywords/data-leakage","display_name":"data leakage","score":0.8149999976158142},{"id":"https://openalex.org/keywords/probability-calibration","display_name":"probability calibration","score":0.9309999942779541},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.8880000114440918},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.7749999761581421},{"id":"https://openalex.org/keywords/clinical-risk-factors","display_name":"clinical risk factors","score":0.7570000290870667},{"id":"https://openalex.org/keywords/glucose","display_name":"glucose","score":0.8349999785423279},{"id":"https://openalex.org/keywords/body-mass-index","display_name":"body mass index","score":1.0},{"id":"https://openalex.org/keywords/age","display_name":"age","score":0.5720000267028809},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.6869999766349792}],"concepts":[{"id":"https://openalex.org/C35405484","wikidata":"https://www.wikidata.org/wiki/Q4967066","display_name":"Brier score","level":2,"score":0.9628999829292297},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167999863624573},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.46970000863075256},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44510000944137573},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4399999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4293999969959259},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35409998893737793},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32899999618530273},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.28619998693466187},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C555293320","wikidata":"https://www.wikidata.org/wiki/Q12206","display_name":"Diabetes mellitus","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.54660/ijmbhr.2026.7.3.168-174","doi":"https://doi.org/10.54660/ijmbhr.2026.7.3.168-174","is_oa":true,"landing_page_url":"https://doi.org/10.54660/ijmbhr.2026.7.3.168-174","pdf_url":null,"source":{"id":"https://openalex.org/S4210185971","display_name":"International Journal of Medical and All Body Health Research","issn_l":"2582-8940","issn":["2582-8940"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Medical and All Body Health Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.54660/ijmbhr.2026.7.3.168-174","doi":"https://doi.org/10.54660/ijmbhr.2026.7.3.168-174","is_oa":true,"landing_page_url":"https://doi.org/10.54660/ijmbhr.2026.7.3.168-174","pdf_url":null,"source":{"id":"https://openalex.org/S4210185971","display_name":"International Journal of Medical and All Body Health Research","issn_l":"2582-8940","issn":["2582-8940"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Medical and All Body Health Research","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.9537000060081482,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4400357606","https://openalex.org/W7204470658","https://openalex.org/W7221509833","https://openalex.org/W7133324668","https://openalex.org/W7203460362","https://openalex.org/W7124887394","https://openalex.org/W4387775550","https://openalex.org/W7162071097","https://openalex.org/W4414500356","https://openalex.org/W4414603547"],"abstract_inverted_index":{"Background:":[0],"Diabetes":[1],"mellitus":[2],"is":[3,13],"a":[4,122,133,203,207,211,221,275],"major":[5],"global":[6],"health":[7],"burden,":[8],"and":[9,21,44,47,59,94,116,127,170,178,220,230,242,257,318],"its":[10],"early":[11],"detection":[12],"essential":[14],"for":[15,66,271,289,312,326],"preventing":[16],"serious":[17],"complications.":[18],"Machine":[19],"learning,":[20],"eXtreme":[22],"Gradient":[23],"Boosting":[24],"(XGBoost)":[25],"in":[26,264],"particular,":[27],"performs":[28],"strongly":[29],"on":[30,153],"routine":[31,74],"clinical":[32,104,268],"data;":[33],"however,":[34],"reported":[35],"results":[36],"are":[37,51],"frequently":[38],"optimistic":[39],"because":[40],"of":[41,70,88,181,197,201,205,209,213,218,224,305],"hold-out":[42,310],"evaluation":[43,81],"data":[45,148],"leakage,":[46],"the":[48,68,119,143,163,166,171,179,236,260,303],"resulting":[49],"models":[50],"often":[52],"difficult":[53],"to":[54,142,146],"interpret.":[55],"Objective:":[56],"To":[57],"develop":[58],"rigorously":[60],"evaluate":[61],"an":[62,78,97,195,199,215],"interpretable":[63],"XGBoost":[64,279],"model":[65,193,314],"predicting":[67],"presence":[69],"diabetes":[71,290],"from":[72],"eight":[73,103],"diagnostic":[75],"measurements,":[76],"using":[77,132,156],"unbiased,":[79],"leakage-controlled":[80],"design.":[82],"Methods:":[83],"An":[84],"openly":[85],"available":[86],"dataset":[87],"1,168":[89],"patient":[90],"records":[91],"(771":[92],"non-diabetic":[93],"397":[95],"diabetic;":[96],"approximately":[98],"66:34":[99],"class":[100],"imbalance)":[101],"with":[102,118,138,186,266,286],"features":[105],"was":[106,151,176,184],"analysed.":[107],"Physiologically":[108],"implausible":[109],"zero":[110],"values":[111],"were":[112,130,239],"treated":[113],"as":[114,246,259],"missing":[115],"imputed":[117],"median":[120],"inside":[121],"processing":[123],"pipeline.":[124],"Model":[125],"selection":[126],"performance":[128,301],"estimation":[129],"separated":[131],"5\u00d75":[134],"nested":[135,306],"cross-validation":[136,307],"scheme,":[137],"all":[139],"preprocessing":[140],"confined":[141],"training":[144],"folds":[145],"prevent":[147],"leakage.":[149],"Performance":[150],"assessed":[152],"out-of-fold":[154],"predictions":[155],"accuracy,":[157],"sensitivity,":[158],"specificity,":[159],"precision,":[160],"F1":[161,216],"score,":[162],"area":[164],"under":[165],"ROC":[167],"curve":[168,229],"(ROC-AUC),":[169],"Brier":[172,222,232],"score;":[173],"probability":[174],"calibration":[175,228],"examined;":[177],"contribution":[180],"each":[182],"feature":[183],"quantified":[185],"SHapley":[187],"Additive":[188],"exPlanations":[189],"(SHAP).":[190],"Results:":[191],"The":[192,226,298],"achieved":[194],"ROC-AUC":[196],"0.823,":[198],"accuracy":[200],"0.769,":[202],"specificity":[204],"0.859,":[206],"sensitivity":[208],"0.595,":[210],"precision":[212],"0.684,":[214],"score":[217,223,233],"0.636,":[219],"0.160.":[225],"near-diagonal":[227],"low":[231],"indicated":[234],"that":[235],"predicted":[237],"probabilities":[238,288],"well":[240],"calibrated":[241],"could":[243],"be":[244],"interpreted":[245],"reliable":[247],"risk":[248,269],"estimates.":[249],"SHAP":[250,293],"analysis":[251],"identified":[252],"glucose,":[253],"body":[254],"mass":[255],"index,":[256],"age":[258],"most":[261],"influential":[262],"predictors,":[263],"agreement":[265],"established":[267],"factors":[270],"diabetes.":[272],"Conclusions:":[273],"Under":[274],"leakage-controlled,":[276],"unbiased":[277],"evaluation,":[278],"provided":[280],"moderate":[281],"but":[282],"trustworthy":[283],"discrimination":[284],"together":[285],"well-calibrated":[287],"prediction,":[291],"while":[292],"confirmed":[294],"clinically":[295],"plausible":[296],"predictors.":[297],"comparatively":[299],"conservative":[300],"underscores":[302],"importance":[304],"over":[308],"simple":[309],"splits":[311],"realistic":[313],"assessment.":[315],"External":[316],"validation":[317],"decision-threshold":[319],"or":[320],"class-imbalance":[321],"strategies":[322],"represent":[323],"promising":[324],"directions":[325],"future":[327],"work.":[328]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-14T00:00:00"}