{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005938907,0.0005211567,0.0007742576,0.0006228971,0.0006918234,0.0007660362,0.0005687217,0.00114415,0.002073278],"category_scores_gemma":[0.02199285,0.0005097251,0.0006668783,0.0004169915,0.0009345938,0.001156303,0.0006059585,0.0008793754,0.0005708155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006657994,"about_ca_system_score_gemma":0.0008937764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001652304,"about_ca_topic_score_gemma":0.001920964,"domain_scores_codex":[0.996472,0.001858326,0.0002887506,0.0005178892,0.0004662437,0.0003968103],"domain_scores_gemma":[0.9798278,0.01293754,0.002219712,0.0009466857,0.002006958,0.002061269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.08006706,0.03134651,0.8546783,0.0001837887,0.0003333428,0.0009061904,0.004712726,0.000342265,0.008961602,0.0001342829,0.00030599,0.018028],"study_design_scores_gemma":[0.003694032,0.2205521,0.7635936,0.00003733736,0.0003983175,0.001507408,0.003580819,0.001684276,0.004044023,0.0001481603,0.0006847539,0.00007521853],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9996659,0.00003006901,0.00004808067,0.00001503807,0.000006415692,0.00005050858,0.00001972365,0.000001225953,0.0001630479],"genre_scores_gemma":[0.9992981,0.0000390863,0.0003507214,0.00005079645,0.00003013248,0.0000617553,0.00004568719,0.000002201203,0.0001215081],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005938907,"threshold_uncertainty_score":0.03140831,"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."}}