{"id":"W2232773008","doi":"10.1186/s13040-015-0078-9","title":"Iteratively refining breast cancer intrinsic subtypes in the METABRIC dataset","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"BC Cancer Agency; Australian Research Council; Cancer Research UK","keywords":"Discriminative model; Computer science; Machine learning; Artificial intelligence; Set (abstract data type); Breast cancer; Class (philosophy); Data mining; Pattern recognition (psychology); Cancer; Medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006578565,0.0001289336,0.0001283753,0.0001348607,0.0001153032,0.0001850618,0.001228204,0.00004039767,0.00005116298],"category_scores_gemma":[0.00006078825,0.00007262917,0.00002017415,0.0006225513,0.00005333847,0.001302769,0.0003569616,0.00009763119,0.00007410496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009965905,"about_ca_system_score_gemma":0.0000844985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003516575,"about_ca_topic_score_gemma":0.00039945,"domain_scores_codex":[0.9986773,0.0001500181,0.000212127,0.0004497655,0.0002399975,0.0002707498],"domain_scores_gemma":[0.9988001,0.0002515865,0.0001155054,0.0007666735,0.00003135241,0.00003480083],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002388513,0.00002327562,0.01179665,0.000008783866,0.00002282951,0.00002672143,0.001358188,0.000002534051,0.002261038,0.001549138,0.01981375,0.9631132],"study_design_scores_gemma":[0.002147567,0.0002068578,0.3935787,0.0006967668,0.00005203018,0.0004697305,0.0005928747,0.002609158,0.007025558,0.0003932452,0.5910686,0.001158843],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5046088,0.005460222,0.3870594,0.07345656,0.006464271,0.001001881,0.01887175,0.0008159541,0.002261138],"genre_scores_gemma":[0.9847666,0.0001262025,0.01327662,0.00124729,0.0002996771,0.00008172485,0.00009313774,0.00001312391,0.00009564235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9619544,"threshold_uncertainty_score":0.2961732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04386414633269161,"score_gpt":0.2884951767383135,"score_spread":0.2446310304056219,"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."}}