{"id":"W4376140206","doi":"10.1093/bjs/znad101.022","title":"O022 Real-time artificial intelligence instructor vs expert instruction in teaching of expert level tumour resection skills – a randomized controlled trial","year":2023,"lang":"en","type":"article","venue":"British journal of surgery","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"CLIPS; Task (project management); Medicine; Baseline (sea); Randomized controlled trial; Benchmark (surveying); Adaptation (eye); Medical education; Medical physics; Artificial intelligence; Computer science; Surgery; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008198676,0.0001840996,0.002059225,0.001198029,0.0001534405,0.00006228124,0.0001116203,0.000212964,0.0001611582],"category_scores_gemma":[0.0134507,0.0001813439,0.0007369971,0.0006826761,0.0001705165,0.0004132334,0.00002422974,0.0006394355,0.00001546499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002452502,"about_ca_system_score_gemma":0.0007859581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004211371,"about_ca_topic_score_gemma":0.0001090477,"domain_scores_codex":[0.9942513,0.001032978,0.003394513,0.0002461022,0.000706632,0.0003685297],"domain_scores_gemma":[0.9946213,0.003150592,0.001286122,0.0001497146,0.0006072934,0.0001849363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.6549504,0.0004908537,0.0004194312,0.00005823243,0.000110305,0.0002407239,0.003238102,0.0000402919,0.007067149,0.00004797403,0.001401092,0.3319354],"study_design_scores_gemma":[0.7080307,0.003559748,0.0169913,0.02186419,0.0005815204,0.01357079,0.04822616,0.009195186,0.1550066,0.02048175,0.0005413013,0.001950783],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925128,0.0004414659,0.0002981313,0.0008708591,0.004480055,0.001229726,0.000004622618,0.00003821695,0.0001240766],"genre_scores_gemma":[0.9903032,0.006414425,0.0005468506,0.00007922282,0.002383153,0.00009860841,0.00001815322,0.0000324772,0.0001239743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3299847,"threshold_uncertainty_score":0.9948594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1382814171599624,"score_gpt":0.3929936111285259,"score_spread":0.2547121939685635,"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."}}