{"id":"W2904004553","doi":"10.1148/radiol.2018181426","title":"Impact of Digital Mammography on Cancer Detection and Recall Rates: 11.3 Million Screening Episodes in the English National Health Service Breast Cancer Screening Program","year":2018,"lang":"en","type":"article","venue":"Radiology","topic":"AI in cancer detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Hospital Foundation","funders":"Public Health England; Cancer Research UK","keywords":"Medicine; Mammography; Cancer detection; Breast cancer; Breast cancer screening; Gynecology; Cancer screening; Family medicine; Cancer; Recall; Obstetrics; Medical physics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001763182,0.0001808968,0.0002648965,0.0006232163,0.0001597457,0.0006134704,0.000402091,0.0002596093,0.0007614027],"category_scores_gemma":[0.009077515,0.0001962564,0.00052187,0.0007119108,0.0002039023,0.000377459,0.0007702378,0.0003300237,0.00009005229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001348306,"about_ca_system_score_gemma":0.0007083011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04274267,"about_ca_topic_score_gemma":0.04232295,"domain_scores_codex":[0.9977349,0.001168461,0.0001923745,0.0002569433,0.0003955414,0.0002517219],"domain_scores_gemma":[0.9942604,0.001767011,0.003000557,0.0002299975,0.0003810958,0.0003608974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009503279,0.00004065764,0.9938223,0.00004204181,0.00006243772,0.00005925001,0.00006586729,0.0001167649,0.0001118237,0.00002068872,0.0002100633,0.005353066],"study_design_scores_gemma":[0.000004926508,0.00005393383,0.9989976,0.00001552755,0.00003675691,0.00009755327,0.0001161875,0.0003225209,0.0001212542,0.000008301744,0.0002228738,0.000002586963],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974747,0.0006709999,0.0001095597,0.0002814978,0.000006765293,0.00001440305,0.0008881047,0.00001021822,0.0005437263],"genre_scores_gemma":[0.9985766,0.0003271029,0.0001526783,0.0001640586,0.00001288517,0.00001151781,0.0005653454,0.000002202823,0.000187624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04274267,"threshold_uncertainty_score":0.08498776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.028080408641976,"score_gpt":0.3347723505787126,"score_spread":0.3066919419367365,"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."}}