{"id":"W3169323730","doi":"10.1007/s11042-021-11114-5","title":"Predicting breast cancer biopsy outcomes from BI-RADS findings using random forests with chi-square and MI features","year":2021,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"AI in cancer detection","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ontario Institute of Technology","funders":"","keywords":"Random forest; Breast cancer; Computer science; Mammography; Classifier (UML); Biopsy; BI-RADS; Feature selection; Artificial intelligence; Estimator; Medicine; Machine learning; Breast cancer screening; Cancer; Radiology; Pattern recognition (psychology); Statistics; Internal medicine; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004272841,0.0009106221,0.001031189,0.003196299,0.0003574515,0.0007555377,0.001073997,0.0007368708,0.001534165],"category_scores_gemma":[0.00900728,0.000292555,0.001487468,0.001087601,0.0002269655,0.0006453745,0.0005400409,0.0008655793,0.0009681567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002827297,"about_ca_system_score_gemma":0.0006230836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004805548,"about_ca_topic_score_gemma":0.006544059,"domain_scores_codex":[0.9990051,0.0003120431,0.0001040907,0.0002376898,0.0001956748,0.0001454534],"domain_scores_gemma":[0.9940281,0.004152745,0.0004759736,0.000259526,0.0007626649,0.0003209539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002207307,0.0008526635,0.7489895,0.0001571479,0.000785604,0.0003555868,0.00008902005,0.03613609,0.005694882,0.000356541,0.00548695,0.1988888],"study_design_scores_gemma":[0.00007897484,0.0005123286,0.1287231,0.00005734588,0.0005350271,0.000632616,0.0001186617,0.8633311,0.003050924,0.001959554,0.0009504474,0.00004990305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.820935,0.001728305,0.1692047,0.0005562582,0.0002455032,0.0001489487,0.003933877,0.002074315,0.001172995],"genre_scores_gemma":[0.9796414,0.0001445075,0.01725423,0.00006535122,0.000125692,0.00005326918,0.00218179,0.00005311851,0.0004806589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004805548,"threshold_uncertainty_score":0.02259719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01907542134954093,"score_gpt":0.2658236636203795,"score_spread":0.2467482422708386,"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."}}