{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07325398,0.001690352,0.002455366,0.003396194,0.0007384366,0.003453143,0.002084605,0.002108182,0.00155127],"category_scores_gemma":[0.1877508,0.0007378996,0.001475092,0.003668165,0.002732543,0.002950258,0.002402723,0.004083756,0.0004029741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010844,"about_ca_system_score_gemma":0.003006023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002131199,"about_ca_topic_score_gemma":0.001721847,"domain_scores_codex":[0.9193141,0.07310569,0.002021698,0.001509451,0.003698687,0.000350277],"domain_scores_gemma":[0.8013338,0.1888973,0.003211485,0.002505795,0.003567514,0.000484037],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003080996,0.0001890167,0.01111928,0.001443528,0.0009231921,0.0006602273,0.00131395,0.2360925,0.0006148086,0.423216,0.007943912,0.3161753],"study_design_scores_gemma":[0.0001087081,0.0002204547,0.001551995,0.000561858,0.0001528043,0.0001654769,0.0001680595,0.4874945,0.0006837909,0.4996164,0.009195459,0.00008045236],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00396704,0.003073339,0.989148,0.002510699,0.0001485836,0.0002073553,0.00006907037,0.000102901,0.0007730297],"genre_scores_gemma":[0.1649728,0.005680989,0.8243889,0.0008243105,0.0006637945,0.001826627,0.0002370698,0.0001461355,0.001259417],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.926746,"threshold_uncertainty_score":0.3874087,"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."}}