{"id":"W2947771303","doi":"10.1016/j.drudis.2019.05.018","title":"Unbiased data analytic strategies to improve biomarker discovery in precision medicine","year":2019,"lang":"en","type":"review","venue":"Drug Discovery Today","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick; Toronto General Hospital","funders":"Diabetes Canada","keywords":"Overfitting; Biomarker discovery; Precision medicine; Computer science; Data science; Analytics; Preprocessor; Data pre-processing; Biomarker; Data mining; Machine learning; Artificial intelligence; Medicine; Proteomics; Biology","routes":{"ca_aff":true,"ca_fund":true,"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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01012915,0.001221541,0.007096048,0.0007313387,0.0000623958,0.0005657088,0.003262289,0.0006651526,0.0003448269],"category_scores_gemma":[0.09425332,0.0008037206,0.0006389195,0.001538118,0.0003229,0.001493441,0.002162991,0.001143265,0.0003268934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003800481,"about_ca_system_score_gemma":0.001073863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002964719,"about_ca_topic_score_gemma":0.0001588777,"domain_scores_codex":[0.9879184,0.003125347,0.004233039,0.002525958,0.001284107,0.0009131009],"domain_scores_gemma":[0.8974781,0.09557781,0.001305741,0.005271621,0.00008568092,0.0002810639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002427278,0.0005359647,0.000008292137,0.03441432,0.0007277221,0.0001253565,0.0001504285,0.000006096323,0.000007020798,0.02851758,0.04586248,0.889402],"study_design_scores_gemma":[0.00197455,0.0003057736,0.00003334109,0.07284269,0.00455308,0.00001032724,0.0003758349,0.0002510083,0.000003680297,0.3404574,0.5772409,0.001951445],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000381828,0.9094791,0.06493787,0.0004135493,0.00572544,0.00685455,0.007759282,0.0001358785,0.004656082],"genre_scores_gemma":[0.0000384645,0.9475742,0.04324143,0.000172424,0.0009360712,0.0002296192,0.0006870003,0.0002784828,0.006842309],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8874506,"threshold_uncertainty_score":0.9994414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6483316119005409,"score_gpt":0.6010919350572403,"score_spread":0.04723967684330055,"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."}}