{"id":"W1980570292","doi":"10.1111/his.12387","title":"Understanding diagnostic variability in breast pathology: lessons learned from an expert consensus review panel","year":2014,"lang":"en","type":"article","venue":"Histopathology","topic":"Breast Lesions and Carcinomas","field":"Medicine","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"National Cancer Institute; National Institutes of Health","keywords":"Medical diagnosis; Consensus conference; Medicine; Medical physics; Atypia; MEDLINE; Diagnostic accuracy; Pathology; Radiology; Internal medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.001596196,0.0002299846,0.0007567118,0.000125017,0.0001016855,0.000006136263,0.0001383731,0.0002578982,0.0003908698],"category_scores_gemma":[0.00153733,0.0002092959,0.0001023379,0.0001863339,0.0003803727,0.0000349278,0.00007044565,0.0004204203,0.00006763133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003689512,"about_ca_system_score_gemma":0.000132084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000260095,"about_ca_topic_score_gemma":0.00009879661,"domain_scores_codex":[0.9969365,0.001355338,0.0004571168,0.0007015812,0.0001453282,0.0004041356],"domain_scores_gemma":[0.9976977,0.001032087,0.0001205327,0.0008686074,0.00006320802,0.0002178504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00133198,0.004472348,0.642094,0.0017929,0.00003661291,0.01540455,0.005396148,0.00001320065,0.1168845,0.06349779,0.01616166,0.1329143],"study_design_scores_gemma":[0.001600724,0.0002120812,0.9795246,0.0007166262,0.0001296034,0.004046722,0.0002257398,0.0002208003,0.00001543565,0.008184565,0.004850075,0.0002730337],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8867959,0.008954588,0.009362344,0.08674143,0.0008917425,0.0008737125,0.0001155072,0.0002564743,0.006008306],"genre_scores_gemma":[0.9913555,0.00149678,0.0008400028,0.005879925,0.0001576139,0.00005962385,0.0001051751,0.00003262838,0.00007276588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3374306,"threshold_uncertainty_score":0.8534841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1957943781271972,"score_gpt":0.3366647818748662,"score_spread":0.140870403747669,"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."}}