{"id":"W2913478113","doi":"10.1016/j.acra.2018.11.022","title":"RE: A Methodological Issue in Prediction of Cancer Masking in Screening Mammography Using Density and Textural Features - Authors’ Response","year":2019,"lang":"en","type":"letter","venue":"Academic Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Masking (illustration); Mammography; MAMMOGRAPHIC DENSITY; Computer science; Cancer; Medicine; Medical physics; Breast cancer; Internal medicine; Art","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":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.003471147,0.0003278193,0.0008538801,0.002031681,0.00005740609,0.00001843249,0.0007362473,0.003069523,0.000006551922],"category_scores_gemma":[0.0005826805,0.0003098357,0.00009792374,0.001448119,0.0002652777,0.000290062,0.0003599156,0.005606299,5.796606e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002919922,"about_ca_system_score_gemma":0.0001091342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001397097,"about_ca_topic_score_gemma":0.00008833496,"domain_scores_codex":[0.9939821,0.003486474,0.0006879027,0.001009473,0.000270688,0.0005633555],"domain_scores_gemma":[0.9966381,0.002308593,0.0005302703,0.0004403446,0.00004506129,0.00003761736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002780048,0.00001841391,0.527404,0.0006055767,0.0003068644,0.0007897213,0.007150651,0.009927501,0.05071586,0.0001446042,0.3494333,0.05072343],"study_design_scores_gemma":[0.002011374,0.0005901563,0.8355429,0.001555502,0.000119946,0.001653225,0.0001744102,0.05686889,0.003253151,0.00370996,0.09335988,0.001160606],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6161845,0.009985825,0.1215956,0.2474525,0.003581081,0.0009835426,0.00002998838,0.0001571449,0.00002977098],"genre_scores_gemma":[0.4861799,0.006499507,0.2323929,0.2665184,0.007485602,0.0002333075,0.00005286711,0.0001566402,0.0004809545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3081389,"threshold_uncertainty_score":0.9999354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1011074908623985,"score_gpt":0.3657631353436656,"score_spread":0.2646556444812671,"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."}}