{"id":"W4413438262","doi":"10.62051/p44xjf14","title":"Dynamic Feature Engineering for Breast Cancer Risk Stratification: A Machine Learning System Integrating Clinical Guidelines","year":2025,"lang":"en","type":"article","venue":"Transactions on Computer Science and Intelligent Systems Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Columbia College","funders":"","keywords":"Risk stratification; Breast cancer; Stratification (seeds); Feature (linguistics); Computer science; Feature engineering; Artificial intelligence; Machine learning; Medicine; Medical physics; Cancer; Internal medicine; Biology; Deep learning","routes":{"ca_aff":true,"ca_fund":false,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.006750596,0.0002101814,0.000294197,0.0009170118,0.001484634,0.001034975,0.001124958,0.0001296637,0.000002291398],"category_scores_gemma":[0.0001216215,0.0001771722,0.00009832394,0.0024921,0.0002433743,0.0006074597,0.00005950141,0.0009994881,0.000007071613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007265221,"about_ca_system_score_gemma":0.0006133058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004806554,"about_ca_topic_score_gemma":0.00008498497,"domain_scores_codex":[0.9966182,0.0002942277,0.0006735038,0.0009883496,0.0009024772,0.0005232625],"domain_scores_gemma":[0.9961519,0.0006867127,0.0001403291,0.0006029867,0.002248431,0.0001696143],"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":[0.00003707448,0.00005768782,0.0002403446,0.0003351978,0.00006662851,0.000001511914,0.000302237,0.1265203,0.0003810975,0.007312093,0.0003290396,0.8644168],"study_design_scores_gemma":[0.0001701997,0.0002148034,0.0003886255,0.0006968768,0.00001019277,0.0000327387,0.0002483674,0.9946206,0.0005887811,0.00003247129,0.002842102,0.0001542419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001479369,0.0007890042,0.9917098,0.001841507,0.002943975,0.000898582,0.00002886407,0.0002588572,0.00005006736],"genre_scores_gemma":[0.9487545,0.0007305793,0.04925092,0.00004551509,0.0002049174,0.0004212646,0.000001335588,0.00001626837,0.0005746879],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9472752,"threshold_uncertainty_score":0.9998153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07515410590438526,"score_gpt":0.4162538166870503,"score_spread":0.341099710782665,"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."}}