{"id":"W4229024550","doi":"10.1093/biostatistics/kxac029","title":"A flexible approach for predictive biomarker discovery","year":2022,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Computer science; False positive paradox; Estimator; Inference; Identification (biology); Nonparametric statistics; False positives and false negatives; Metric (unit); Biomarker discovery; Multiple comparisons problem; Predictive inference; Biomarker; Data mining; False discovery rate; Truncation (statistics); Machine learning; Artificial intelligence; Statistics; Frequentist inference; Mathematics; Bayesian probability; Bayesian inference","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002352662,0.0002154687,0.0005068977,0.00008806228,0.0003520396,0.0000652887,0.0003550282,0.00008013376,0.0002737933],"category_scores_gemma":[0.04407732,0.0002012856,0.000152611,0.0002986236,0.0001886299,0.00006244162,0.0003145435,0.0002487088,0.0000045918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001421209,"about_ca_system_score_gemma":0.0001206574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005763402,"about_ca_topic_score_gemma":3.080478e-7,"domain_scores_codex":[0.997259,0.0006025428,0.0007280234,0.0004941092,0.0005109782,0.0004053166],"domain_scores_gemma":[0.9653872,0.03364698,0.0002844793,0.0004508413,0.0001112302,0.0001193206],"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":[0.0009384062,0.0007887019,0.0001456417,0.0002930538,0.0002128813,0.00001136739,0.0001588398,0.00006385383,0.000233092,0.8488368,0.1377421,0.01057534],"study_design_scores_gemma":[0.001328412,0.0005638342,0.0002771264,0.000008812118,0.0001976488,0.000009783034,0.000329225,0.01628281,0.0002667394,0.9727488,0.007691543,0.0002953025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002054326,0.00003621521,0.9808348,0.0001164749,0.0008797644,0.001298468,0.01269792,0.0001519419,0.003778973],"genre_scores_gemma":[0.01749525,0.00000600271,0.9787448,0.000253806,0.0002067643,0.0008528697,0.0001046083,0.00007007119,0.002265849],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1300505,"threshold_uncertainty_score":0.9639748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5564742844991701,"score_gpt":0.5379670415846817,"score_spread":0.01850724291448846,"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."}}