{"id":"W4408657832","doi":"10.1097/ccm.0000000000006629","title":"Artificial Intelligence-Guided Bronchoscopy is Superior to Human Expert Instruction for the Performance of Critical-Care Physicians: A Randomized Controlled Trial","year":2025,"lang":"en","type":"article","venue":"Critical Care Medicine","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Thomas Hospital","funders":"","keywords":"Medicine; Flexible bronchoscopy; Randomized controlled trial; TUTOR; Bronchoscopy; Observational study; Physical therapy; Psychological intervention; Test (biology); Medical physics; Surgery; Nursing; Internal medicine; 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":[0.0006706355,0.0002470343,0.001687007,0.0001936013,0.000300473,0.00002269836,0.000143291,0.0001448701,0.0006149582],"category_scores_gemma":[0.01092783,0.0001470282,0.0004653518,0.000387084,0.001177652,0.0000616709,0.00003380415,0.0002458168,0.000004946382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008804707,"about_ca_system_score_gemma":0.0001167585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003431165,"about_ca_topic_score_gemma":0.000003998587,"domain_scores_codex":[0.9974051,0.000161623,0.001200323,0.0003752102,0.0005126814,0.0003450392],"domain_scores_gemma":[0.9930316,0.005173239,0.00005870243,0.0003372484,0.001234354,0.0001648878],"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":[0.8427125,0.0002049701,0.00004403905,0.001054385,0.0001735177,0.000004807136,0.01156716,0.00001856871,0.00139821,0.04143512,0.0002528198,0.1011339],"study_design_scores_gemma":[0.922391,0.003198097,0.00005445566,0.001655124,0.00177948,0.000003968406,0.04523551,0.007545528,0.01356922,0.001471818,0.002839395,0.0002564121],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8896534,0.004895689,0.03247042,0.04874291,0.004611579,0.01178035,0.00002454058,0.0001562163,0.007664871],"genre_scores_gemma":[0.9920151,0.00002312933,0.000451887,0.005107453,0.001286865,0.0009948778,0.00002719445,0.00002061237,0.00007289325],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1023617,"threshold_uncertainty_score":0.9974036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0666105890759742,"score_gpt":0.421817084853882,"score_spread":0.3552064957779077,"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."}}