{"id":"W4402601437","doi":"10.1148/ryai.230550","title":"Assessing the Performance of Models from the 2022 RSNA Cervical Spine Fracture Detection Competition at a Level I Trauma Center","year":2024,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"St. Michael's Hospital Foundation","keywords":"Cervical spine; Center (category theory); Trauma center; Medicine; Competition (biology); Internal medicine; Surgery; Retrospective cohort study","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003245928,0.0001232295,0.0001725121,0.00004371991,0.0001654159,0.00005264594,0.0002118064,0.000106094,0.0004190698],"category_scores_gemma":[0.00003372016,0.00007283819,0.00009997132,0.0002369991,0.000216193,0.0001541858,0.00002972118,0.0004581547,0.00005982404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000584882,"about_ca_system_score_gemma":0.00001069933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006051224,"about_ca_topic_score_gemma":0.00006501253,"domain_scores_codex":[0.9990473,0.0001054984,0.0003198085,0.0001917512,0.000148476,0.0001871661],"domain_scores_gemma":[0.9994077,0.0002895053,0.00003186166,0.0002055817,0.00002891124,0.00003640546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002243093,0.00005816674,0.0007036063,0.0001240759,0.0003145998,0.00001638645,0.002613578,0.4608134,0.06229382,0.002259088,0.0007226893,0.4700582],"study_design_scores_gemma":[0.00001050477,0.00001706024,0.00120059,0.00007095822,0.00004493277,0.00002012563,0.0001840838,0.9450349,0.05066875,0.001874868,0.0007939105,0.00007936702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.56828,0.001068284,0.4290023,0.0008957881,0.0004792403,0.00005047497,0.0000125177,0.00007421317,0.0001371821],"genre_scores_gemma":[0.9989496,0.0002288166,0.0001792166,0.0001895475,0.0003768805,0.00001077831,0.00002486472,0.00001373753,0.00002654305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4842215,"threshold_uncertainty_score":0.458852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05115680240699588,"score_gpt":0.2940749643982224,"score_spread":0.2429181619912265,"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."}}