{"id":"W2887188207","doi":"10.1016/j.acra.2018.06.011","title":"Prediction of Cancer Masking in Screening Mammography Using Density and Textural Features","year":2018,"lang":"en","type":"article","venue":"Academic Radiology","topic":"Digital Radiography and Breast Imaging","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Masking (illustration); Mammography; Medicine; Confidence interval; Breast cancer; Receiver operating characteristic; Multivariate statistics; Logistic regression; Density estimation; Cancer; Pattern recognition (psychology); Statistics; Artificial intelligence; Mathematics; Computer science; 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":[0.000197008,0.0001071003,0.0002743769,0.000765264,0.00004382331,0.000003825243,0.00005567007,0.000189036,0.000006252117],"category_scores_gemma":[0.00004556941,0.00009305344,0.00005738057,0.0006890931,0.0004619507,0.0001464601,0.00003296477,0.000390328,1.83954e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001773876,"about_ca_system_score_gemma":0.00002110524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000402404,"about_ca_topic_score_gemma":0.00002338401,"domain_scores_codex":[0.9991744,0.00003859748,0.0002337925,0.0002234192,0.00008696379,0.0002428373],"domain_scores_gemma":[0.9996556,0.00005193676,0.00009313634,0.00008966206,0.00004305642,0.00006659826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001670194,0.000006905721,0.9356069,0.00002828828,0.00005901594,0.000009390908,0.0002768435,0.000007965851,0.03517529,0.0001432501,0.0001572505,0.02836186],"study_design_scores_gemma":[0.0007108788,0.0001155538,0.9915504,0.000277549,0.0000726724,0.001331262,0.0001330247,0.001024528,0.004141768,0.0003283883,0.0002404349,0.00007353517],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9950982,0.003283149,0.0004787791,0.0003297707,0.0001478258,0.0001271584,0.000008204137,0.00002760259,0.0004993464],"genre_scores_gemma":[0.9975591,0.0004417895,0.001340786,0.0002893374,0.0003361149,0.000003158165,0.000006078669,0.000009533096,0.00001406902],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05594349,"threshold_uncertainty_score":0.3794609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0296626673613417,"score_gpt":0.3062884094902014,"score_spread":0.2766257421288597,"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."}}