{"id":"W2571736444","doi":"10.1109/bibm.2016.7822749","title":"A new feature selection approach for optimizing prediction models, applied to breast cancer subtype classification","year":2016,"lang":"en","type":"article","venue":"","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Feature selection; Computer science; Classifier (UML); Artificial intelligence; Generality; Pattern recognition (psychology); Feature (linguistics); Machine learning; Greedy algorithm; Data mining; Selection (genetic algorithm); Algorithm","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":[0.002309275,0.00147299,0.001635287,0.001810746,0.0003994247,0.0006964291,0.00101349,0.0007919261,0.001019392],"category_scores_gemma":[0.003755788,0.0005408914,0.00179905,0.002013661,0.0002857361,0.0006555101,0.0005550587,0.0008842891,0.0004275033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004345236,"about_ca_system_score_gemma":0.0008214145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002532279,"about_ca_topic_score_gemma":0.002990556,"domain_scores_codex":[0.9990574,0.0003273116,0.0001026376,0.0002048994,0.0002592539,0.00004846755],"domain_scores_gemma":[0.9987683,0.0006380586,0.00009183305,0.0001024313,0.0003721892,0.0000272257],"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":[0.0001819753,0.0001964472,0.003901989,0.0002373073,0.0005351568,0.0002155774,0.0000744243,0.2879838,0.01496309,0.003407321,0.004811375,0.6834915],"study_design_scores_gemma":[0.00003613102,0.0001510795,0.00129401,0.00001237558,0.00007412069,0.0001125539,0.00001003995,0.9909871,0.002928464,0.002367516,0.002006268,0.00002039247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005693543,0.000217506,0.9929437,0.00006616019,0.00003732027,0.00006794639,0.0001363342,0.0006327045,0.0002046591],"genre_scores_gemma":[0.1719626,0.0003911138,0.8245462,0.0001388943,0.0001348754,0.0005886926,0.0008946445,0.0002138459,0.00112915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002532279,"threshold_uncertainty_score":0.01221275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02364541868890544,"score_gpt":0.2576663546019947,"score_spread":0.2340209359130893,"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."}}