{"id":"W3196024289","doi":"10.1093/biostatistics/kxab032","title":"Predicting the onset of breast cancer using mammogram imaging data with irregular boundary","year":2021,"lang":"en","type":"article","venue":"Biostatistics","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Breast Cancer Research Foundation","keywords":"Breast cancer; Computer science; Artificial intelligence; Mammography; Pattern recognition (psychology); Benchmark (surveying); Breast cancer screening; Boundary (topology); Machine learning; Medicine; Cancer; Mathematics","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":[0.0002201984,0.0001040767,0.0001133394,0.00003252683,0.0002174131,0.0001790706,0.0007120217,0.00002167011,0.00001312965],"category_scores_gemma":[0.00004686746,0.00007951217,0.000014179,0.0004554068,0.0001783228,0.0003030362,0.0005372582,0.0001231888,8.66026e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008553967,"about_ca_system_score_gemma":0.0006232313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006501518,"about_ca_topic_score_gemma":0.0003008989,"domain_scores_codex":[0.9988573,0.0000744207,0.0001903648,0.0003482807,0.0003293031,0.000200387],"domain_scores_gemma":[0.9983574,0.0001314156,0.0001667511,0.001079615,0.0002235714,0.00004127465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007553364,0.0001575265,0.2306684,0.0003643109,0.0003100655,0.0005152583,0.001950582,0.002785411,0.005217794,0.004551267,0.008768682,0.7446352],"study_design_scores_gemma":[0.0003320103,0.00003008956,0.0489377,0.0002552911,0.0001021808,0.001375445,0.000341842,0.9400447,0.002503857,0.0007995823,0.005022906,0.0002544108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01358042,0.0007707403,0.9825446,0.001035996,0.0006090642,0.00009860457,0.001255375,0.00006187687,0.00004332933],"genre_scores_gemma":[0.6590741,0.00006463503,0.3403669,0.0002354459,0.0001631577,0.000005001659,0.00004575408,0.00002073618,0.00002427871],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9372593,"threshold_uncertainty_score":0.3242412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02508658907445413,"score_gpt":0.2886221632118421,"score_spread":0.2635355741373879,"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."}}