{"id":"W4410861246","doi":"10.1007/s00330-025-11687-x","title":"More than density: validating a mammographic masking prediction model in Dutch breast cancer screening","year":2025,"lang":"en","type":"article","venue":"European Radiology","topic":"Digital Radiography and Breast Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research; Sunnybrook Health Science Centre","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Government of Ontario","keywords":"Medicine; Mammography; Breast cancer; Confidence interval; Masking (illustration); Neuroradiology; Receiver operating characteristic; Retrospective cohort study; Cohort; Radiology; Breast cancer screening; Area under the curve; Cancer; Interventional radiology; Digital mammography; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004774902,0.000207894,0.000350885,0.0007653577,0.0001038703,0.00003811745,0.0001424369,0.00006169249,0.00001039716],"category_scores_gemma":[0.0000435634,0.00019782,0.0001568835,0.0008606329,0.0001586735,0.0001774471,0.00009712381,0.0003940154,0.000003668609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005196458,"about_ca_system_score_gemma":0.00005776221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008987398,"about_ca_topic_score_gemma":0.00001830964,"domain_scores_codex":[0.9984493,0.0001692742,0.0003715754,0.0004513434,0.0001305856,0.0004278822],"domain_scores_gemma":[0.9994265,0.00005032914,0.00008679579,0.0002748466,0.00006417577,0.00009731458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002258783,0.00006910293,0.9306579,0.00007735626,0.0001525175,0.0003158736,0.0003833909,0.003359944,0.002439915,0.0004459211,0.0004047758,0.06146739],"study_design_scores_gemma":[0.001395573,0.000044243,0.9401728,0.0007717136,0.0001129251,0.001377073,0.0002721529,0.05524585,0.0001054114,0.0001863363,0.0001497298,0.0001662159],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9559287,0.0004079359,0.02000882,0.002044796,0.0001953066,0.0002453154,0.00003956363,0.0002099577,0.02091955],"genre_scores_gemma":[0.9968268,0.00006588073,0.0014028,0.001079878,0.0001797062,0.00001194293,0.0000448142,0.00003581878,0.0003524086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06130118,"threshold_uncertainty_score":0.8066868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01333245123002377,"score_gpt":0.2664506013973381,"score_spread":0.2531181501673143,"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."}}