{"id":"W3008867523","doi":"10.1136/fmch-2019-000262","title":"Variable selection strategies and its importance in clinical prediction modelling","year":2020,"lang":"en","type":"article","venue":"Family Medicine and Community Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":995,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Akaike information criterion; Feature selection; Selection (genetic algorithm); Bayesian information criterion; Variable (mathematics); Statistic; Computer science; Model selection; Bayesian probability; Statistics; Machine learning; Mathematics; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01005301,0.0001274527,0.0006767143,0.00004162043,0.000234554,0.00001742101,0.0001064451,0.0001357157,0.00001594931],"category_scores_gemma":[0.01944612,0.0001072508,0.0000188085,0.0002734374,0.0001237478,0.000123907,0.00007031023,0.001498142,7.512419e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002966118,"about_ca_system_score_gemma":0.0001920666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009129336,"about_ca_topic_score_gemma":0.0001183275,"domain_scores_codex":[0.9948822,0.003311231,0.001199439,0.0002105164,0.0001840135,0.0002126064],"domain_scores_gemma":[0.9792271,0.01998949,0.0002490451,0.0001785775,0.00007177663,0.0002839926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009165059,0.001075353,0.04875666,0.004643594,0.0001202929,0.000009048196,0.012408,0.000410388,0.0001434301,0.8972015,0.008274673,0.02604058],"study_design_scores_gemma":[0.00192104,0.002264617,0.01119576,0.0004515204,0.000035626,0.000004072344,0.007193748,0.1115585,0.000001491718,0.8648952,0.0003655464,0.000112889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5616601,0.00124881,0.4302222,0.004276982,0.0002240054,0.0005709663,0.00002327344,0.0001178626,0.001655909],"genre_scores_gemma":[0.6571102,0.002753652,0.3344667,0.005197659,0.0004226446,0.00001534603,0.00000586435,0.00001957995,0.000008304338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1111481,"threshold_uncertainty_score":0.9888135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7929098891837675,"score_gpt":0.5963941095425003,"score_spread":0.1965157796412672,"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."}}