{"id":"W4413940286","doi":"10.1007/s10549-025-07801-8","title":"Natural language processing for local, regional, and distant breast cancer relapse identification in pathology reports","year":2025,"lang":"en","type":"article","venue":"Breast Cancer Research and Treatment","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"","keywords":"Breast cancer; Medicine; Cancer; Cohort; Oncology; Receiver operating characteristic; Pathology; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01240695,0.001313162,0.0007348456,0.008051055,0.0008759258,0.002516288,0.001785944,0.0009358387,0.001442452],"category_scores_gemma":[0.04812814,0.0005312352,0.001565637,0.003414082,0.000937542,0.00274323,0.001871648,0.001575805,0.001463188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002463066,"about_ca_system_score_gemma":0.003647676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01626929,"about_ca_topic_score_gemma":0.0186705,"domain_scores_codex":[0.9915558,0.003666898,0.001406816,0.001858288,0.001274782,0.0002374701],"domain_scores_gemma":[0.933487,0.04823156,0.008405922,0.002847115,0.00648197,0.0005464902],"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":[0.001043598,0.0008528422,0.2357585,0.004680699,0.0006002148,0.003271336,0.004755407,0.07289028,0.02671909,0.005197141,0.05760808,0.5866228],"study_design_scores_gemma":[0.0001393859,0.0002839811,0.07686171,0.0008541151,0.0003863565,0.001844758,0.002279578,0.8436217,0.0205525,0.01709165,0.03587342,0.0002109364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3454671,0.003922098,0.5681613,0.005972415,0.000429692,0.003129583,0.04115491,0.02600802,0.005754841],"genre_scores_gemma":[0.5361181,0.000859149,0.4151697,0.0007437674,0.000238801,0.001341274,0.04415241,0.0004051478,0.0009715729],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01626929,"threshold_uncertainty_score":0.06561506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02888630840797602,"score_gpt":0.3733662095331197,"score_spread":0.3444799011251437,"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."}}