{"id":"W4386010662","doi":"10.5267/j.ijdns.2023.8.009","title":"Employing CNN ensemble models in classifying dental caries using oral photographs","year":2023,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Population; Ensemble learning; Dentistry; Computer vision; Pattern recognition (psychology); Orthodontics; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001312288,0.00008988926,0.0001487109,0.0006356082,0.0001854394,0.0004597754,0.001213206,0.00002505116,0.000009743987],"category_scores_gemma":[0.00006041662,0.00008315704,0.00005101656,0.001227656,0.0003124355,0.003533834,0.0006026442,0.0001993446,0.000003302903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004977294,"about_ca_system_score_gemma":0.00009197997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000141842,"about_ca_topic_score_gemma":0.0001575663,"domain_scores_codex":[0.9983157,0.00003235343,0.000368767,0.0002352498,0.0007630586,0.0002848553],"domain_scores_gemma":[0.9993339,0.00008504373,0.0002009765,0.0001619304,0.0001283395,0.0000898471],"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":[0.0001345844,0.00005810369,0.9308471,0.00001038701,0.0001065903,0.001377399,0.0007097922,0.01668359,0.01828543,0.0008599309,0.001729724,0.02919736],"study_design_scores_gemma":[0.001451034,0.00005008836,0.1460816,0.0007132664,0.00004927145,0.003141284,0.00274979,0.8341293,0.00114332,0.009369509,0.0007657114,0.0003558556],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903799,0.0004901696,0.006679719,0.00003319242,0.002054528,0.00003616849,0.00002814234,0.00001395531,0.0002841969],"genre_scores_gemma":[0.9954684,0.0002710184,0.003903307,0.00008168275,0.0002451858,3.78781e-7,0.00001188428,0.000007011407,0.00001112028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8174458,"threshold_uncertainty_score":0.4433624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1018106490359992,"score_gpt":0.3728873888566223,"score_spread":0.271076739820623,"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."}}