{"id":"W4411040734","doi":"10.1016/j.jdent.2025.105877","title":"Large language models for the screening step in systematic reviews in dentistry","year":2025,"lang":"en","type":"article","venue":"Journal of Dentistry","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Dentistry; Orthodontics; Computer science; Medicine","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2148862,0.00563844,0.01725354,0.01887639,0.002920307,0.009129765,0.006989792,0.006213181,0.009163226],"category_scores_gemma":[0.5216806,0.005150482,0.02459352,0.016639,0.002884103,0.01032426,0.007046345,0.007411074,0.002076596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004713333,"about_ca_system_score_gemma":0.01763356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01129819,"about_ca_topic_score_gemma":0.04028989,"domain_scores_codex":[0.6805094,0.2773862,0.02403287,0.009999349,0.007209975,0.0008621807],"domain_scores_gemma":[0.1833534,0.7924024,0.009715496,0.00955913,0.004026782,0.0009427768],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01153204,0.001020644,0.03186699,0.176665,0.1683931,0.002022377,0.003879964,0.1637049,0.00232744,0.05042963,0.04168563,0.3464723],"study_design_scores_gemma":[0.006856117,0.001888475,0.006116157,0.02244912,0.1220127,0.001185436,0.0007287076,0.5885987,0.001297334,0.2256002,0.02253894,0.0007280456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02934892,0.1192392,0.7866995,0.01297217,0.001680351,0.01029065,0.02839053,0.00884348,0.002535286],"genre_scores_gemma":[0.3056703,0.01259496,0.643568,0.003202653,0.0008568156,0.02037484,0.01179829,0.0007516934,0.001182498],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7851138,"threshold_uncertainty_score":0.9681851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1994065509622011,"score_gpt":0.4799455652121281,"score_spread":0.280539014249927,"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."}}