{"id":"W4403380110","doi":"10.6000/1929-6029.2024.13.21","title":"Performance of the Classical Model in Feature Selection Across Varying Database Sizes of Healthcare Data","year":2024,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Feature selection; Feature (linguistics); Computer science; Selection (genetic algorithm); Database; Health care; Data mining; Artificial intelligence; Pattern recognition (psychology); Economics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01676131,0.001283712,0.001508123,0.001834812,0.0007779451,0.001899576,0.00151561,0.001057905,0.001791272],"category_scores_gemma":[0.03789521,0.0003458843,0.002102802,0.002253246,0.0005485386,0.0021577,0.001417098,0.001338603,0.0006615284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008979209,"about_ca_system_score_gemma":0.001888865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01107277,"about_ca_topic_score_gemma":0.006177478,"domain_scores_codex":[0.9929367,0.003803495,0.0006628013,0.00128839,0.0009828272,0.0003257701],"domain_scores_gemma":[0.9812758,0.01468154,0.0005770295,0.001640769,0.001619022,0.000205826],"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":[0.003616667,0.0009733607,0.1330287,0.0009559539,0.001966819,0.0006281966,0.0005258294,0.3980001,0.002965119,0.004972557,0.01401269,0.438354],"study_design_scores_gemma":[0.000105803,0.000445322,0.02280857,0.000111009,0.0002347535,0.0002637875,0.0002589872,0.96615,0.001981221,0.005314234,0.002268316,0.0000579898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6319596,0.005576985,0.3491093,0.00223693,0.0004261751,0.0005215222,0.003981965,0.00224447,0.003943136],"genre_scores_gemma":[0.8854127,0.001019074,0.1060962,0.0003675488,0.0001037504,0.0005084845,0.005141061,0.0001233311,0.001227893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01676131,"threshold_uncertainty_score":0.08864331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09428672363252123,"score_gpt":0.4837787701549981,"score_spread":0.3894920465224769,"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."}}