{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008274548,0.000272962,0.0004653202,0.001736716,0.0005595682,0.001087256,0.0004602984,0.00052219,0.0006075829],"category_scores_gemma":[0.03483373,0.000346,0.0004830249,0.001156385,0.0007599283,0.0007462394,0.0008535701,0.0004188833,0.0001786113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008544872,"about_ca_system_score_gemma":0.0008300953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006961903,"about_ca_topic_score_gemma":0.01286028,"domain_scores_codex":[0.9923653,0.003980856,0.001100889,0.0008569228,0.001196164,0.0004999149],"domain_scores_gemma":[0.9727085,0.01493796,0.003935555,0.001304415,0.006401495,0.0007120708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002784821,0.00005962529,0.992582,0.00002376809,0.0001059888,0.00004559912,0.001199913,0.0001902727,0.0005688522,0.00003531964,0.0001790791,0.004731168],"study_design_scores_gemma":[0.00002108777,0.0002562765,0.9936914,0.00001776971,0.00008430775,0.0002127559,0.002081768,0.002618693,0.0006234287,0.00006443075,0.0003116522,0.00001632218],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989638,0.0001202289,0.0003346219,0.00003382977,0.00001097207,0.00001262979,0.00006164605,0.000008665908,0.000453502],"genre_scores_gemma":[0.9992513,0.0000404744,0.0005099133,0.00001608907,0.000008732849,0.000009065143,0.00008132109,0.000004126783,0.00007894947],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008274548,"threshold_uncertainty_score":0.04376048,"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."}}