{"id":"W3175051613","doi":"10.1007/s00261-021-03193-7","title":"Diagnostic accuracy and inter-observer reliability of the O-RADS scoring system among staff radiologists in a North American academic clinical setting","year":2021,"lang":"en","type":"article","venue":"Abdominal Radiology","topic":"Cervical Cancer and HPV Research","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"RSNA Research and Education Foundation","keywords":"Medicine; Radiology; Ultrasound; Reliability (semiconductor); Malignancy; BI-RADS; Diagnostic accuracy; Medical physics; Cancer; Mammography; Internal medicine; Breast cancer","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":[0.001470694,0.0001606643,0.0008511851,0.00006736345,0.00005641525,0.000006891777,0.0002421786,0.0001558273,0.00003946108],"category_scores_gemma":[0.01591733,0.0001110565,0.0001627186,0.0005197269,0.001318908,0.00005892934,0.0003548726,0.001296285,0.000002697194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002215247,"about_ca_system_score_gemma":0.0003061132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006523454,"about_ca_topic_score_gemma":0.001400577,"domain_scores_codex":[0.9969491,0.001032562,0.0008619054,0.0005298798,0.0001936584,0.0004329219],"domain_scores_gemma":[0.9936746,0.005212167,0.0002438487,0.000512066,0.000171547,0.0001858195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005096543,0.00006380288,0.9478574,0.0003863666,0.00003397137,0.0001717538,0.0002417651,0.00002291424,0.0001109414,0.00003972946,0.00005879639,0.05050289],"study_design_scores_gemma":[0.001347988,0.0004757117,0.9954412,0.000173448,0.00006631439,0.0003380887,0.000861328,0.0009248657,0.0001560877,0.00002024203,0.0000965964,0.00009816072],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970815,0.0009415345,0.00005965568,0.0009758151,0.0002242884,0.0004221753,0.000007737955,0.00001872829,0.0002686318],"genre_scores_gemma":[0.9985466,0.0007802704,0.0001667518,0.000168845,0.0002557636,0.00004229163,0.000006265826,0.00001455507,0.00001867585],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05040473,"threshold_uncertainty_score":0.992372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03766064579377493,"score_gpt":0.3748296889361198,"score_spread":0.3371690431423449,"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."}}