{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007219676,0.0005923762,0.0005420382,0.0007019737,0.0002626194,0.0008729871,0.0007342831,0.0006067753,0.0008897298],"category_scores_gemma":[0.02758155,0.0002451969,0.0007636739,0.0005397286,0.0002297138,0.0004976511,0.0007459667,0.0002801763,0.0003617989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094957,"about_ca_system_score_gemma":0.001065046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03896393,"about_ca_topic_score_gemma":0.02604176,"domain_scores_codex":[0.9979743,0.001192187,0.0001415918,0.0003905798,0.0002319092,0.00006948734],"domain_scores_gemma":[0.9930695,0.004665746,0.0005985217,0.0005113635,0.000957447,0.000197312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001601414,0.0004463169,0.8655179,0.0001581592,0.0008352878,0.0002626518,0.00047761,0.06843457,0.003127716,0.0003331637,0.001118853,0.05768638],"study_design_scores_gemma":[0.000200391,0.0007778574,0.3527021,0.00005266151,0.0003002688,0.000370704,0.000301881,0.6403222,0.002849994,0.0004270567,0.001653054,0.00004169251],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9936967,0.0001223106,0.00505785,0.00006548032,0.000009188819,0.00004242097,0.0005902853,0.00004364277,0.000372004],"genre_scores_gemma":[0.9922413,0.00006305071,0.005812522,0.00002681562,0.000007675811,0.00006056812,0.001502248,0.00001628494,0.0002695658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03896393,"threshold_uncertainty_score":0.07747424,"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."}}