{"id":"W2765388298","doi":"10.1016/j.compbiomed.2017.10.021","title":"Comparison of variable selection methods for high-dimensional survival data with competing events","year":2017,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Ferroptosis and cancer prognosis","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute of Cancer Research; Institut National Du Cancer; Agence Nationale de la Recherche","keywords":"Random forest; Boosting (machine learning); Resampling; Computer science; Data mining; Context (archaeology); Feature selection; Machine learning; Sample size determination; Stability (learning theory); Artificial intelligence; Statistics; Mathematics; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.07596117,0.001544941,0.002636258,0.00241943,0.0008619365,0.001716178,0.003299032,0.001664134,0.004159646],"category_scores_gemma":[0.09706555,0.0006062424,0.004264169,0.002050177,0.001036151,0.001854952,0.001756511,0.002807915,0.000424123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000899069,"about_ca_system_score_gemma":0.002625155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003869126,"about_ca_topic_score_gemma":0.003156664,"domain_scores_codex":[0.9674028,0.02960478,0.0008374587,0.00082387,0.0009538393,0.00037722],"domain_scores_gemma":[0.6468939,0.3444495,0.002163385,0.003081495,0.002496825,0.0009147211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01948439,0.0009465797,0.05756829,0.00189044,0.008042522,0.0002518157,0.0007805973,0.4867831,0.0009054746,0.01957995,0.006326702,0.39744],"study_design_scores_gemma":[0.001316875,0.001149128,0.008564725,0.0001291297,0.0006252005,0.0001451153,0.0001673336,0.9744861,0.000533411,0.01190245,0.0009156835,0.00006491512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2750424,0.008301818,0.7094736,0.0023663,0.0004525143,0.0006913778,0.001459992,0.001109125,0.001102926],"genre_scores_gemma":[0.7771888,0.002479301,0.2128899,0.0005238039,0.0003873847,0.001175244,0.003228061,0.0003269826,0.001800654],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07596117,"threshold_uncertainty_score":0.4017259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09216229628866375,"score_gpt":0.462077198074063,"score_spread":0.3699149017853993,"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."}}