{"id":"W4406154079","doi":"10.1186/s12903-025-05419-2","title":"Early childhood caries risk prediction using machine learning approaches in Bangladesh","year":2025,"lang":"en","type":"article","venue":"BMC Oral Health","topic":"Dental Health and Care Utilization","field":"Dentistry","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Universitetet i Bergen","keywords":"Medicine; Machine learning; Artificial intelligence; Random forest; Interpretability; AdaBoost; Early childhood caries; Receiver operating characteristic; Feature selection; Support vector machine; Gradient boosting; Dentistry; Oral health; Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001498347,0.0007991373,0.0005209774,0.001303641,0.0002423756,0.0007750109,0.0005310207,0.0004950502,0.001222628],"category_scores_gemma":[0.003102902,0.000249398,0.0007280272,0.000648853,0.0001783386,0.0003990548,0.0005294447,0.0006680918,0.0004575867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009668847,"about_ca_system_score_gemma":0.0006793684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01963241,"about_ca_topic_score_gemma":0.01110454,"domain_scores_codex":[0.9995736,0.0001933082,0.00004643255,0.00008185448,0.00006035778,0.00004429214],"domain_scores_gemma":[0.9986374,0.0009756513,0.0001207172,0.00004545426,0.0001689813,0.00005190178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006456103,0.0004106111,0.5981495,0.0002253295,0.0004215824,0.0005391802,0.0004612856,0.2691461,0.002129162,0.000772407,0.001462865,0.1256362],"study_design_scores_gemma":[0.00003480046,0.0002830954,0.09224701,0.000113146,0.0001006405,0.000238859,0.000549129,0.902041,0.001224925,0.001886983,0.001237264,0.00004314769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9780031,0.001074542,0.01676909,0.0007088954,0.00001657992,0.00008816001,0.001110167,0.00008857134,0.002141028],"genre_scores_gemma":[0.9927731,0.0003630387,0.005706833,0.00002562933,0.000007451074,0.00005037787,0.0006311788,0.000005123579,0.0004372744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01963241,"threshold_uncertainty_score":0.03903627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05345303949449401,"score_gpt":0.3216324316114507,"score_spread":0.2681793921169567,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}