{"id":"W4416224015","doi":"10.1007/s10140-025-02415-5","title":"Diagnostic performance of radiology residents versus attending radiologists in detecting retained surgical items: a pilot study","year":2025,"lang":"en","type":"article","venue":"Emergency Radiology","topic":"Hemostasis and retained surgical items","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Medical diagnosis; Service (business); MEDLINE; Diagnostic accuracy; Computed tomography; Surgical procedures","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001638761,0.0003423303,0.001357499,0.0005994218,0.0001296679,0.000003763878,0.000294963,0.000251952,0.0002740415],"category_scores_gemma":[0.003708592,0.000276559,0.0001681702,0.001112991,0.000266981,0.00006544591,0.0001361577,0.0006697593,0.00001605575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001954506,"about_ca_system_score_gemma":0.0001401824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003598289,"about_ca_topic_score_gemma":0.0001067844,"domain_scores_codex":[0.9959624,0.0008769563,0.001461592,0.0007141332,0.0002099794,0.0007749513],"domain_scores_gemma":[0.9969215,0.002033501,0.0002501443,0.0005427434,0.0001002734,0.0001518226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005285338,0.0008031726,0.9862515,0.0001659068,0.00033985,0.0008478599,0.0003822122,0.0001843448,0.002384366,0.0002358737,0.000734883,0.002384652],"study_design_scores_gemma":[0.01434995,0.01490587,0.9642175,0.0002652582,0.0002336299,0.0006679281,0.0009950963,0.002322589,0.0004603912,0.00007845435,0.001087157,0.0004161265],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890519,0.004281405,0.00002886689,0.0004523564,0.002107818,0.001026604,0.000003795294,0.00007067421,0.002976623],"genre_scores_gemma":[0.9965597,0.002405589,0.00005873834,0.00003195415,0.0002314595,0.00009130572,0.00002432189,0.00002503352,0.0005719221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02203399,"threshold_uncertainty_score":0.9999686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04747699888181226,"score_gpt":0.3423520659285565,"score_spread":0.2948750670467443,"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."}}