{"id":"W2736786428","doi":"10.1002/sim.8673","title":"Developing biomarker combinations in multicenter studies via direct maximization and penalization","year":2020,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Pritzker School of Medicine; National Institutes of Health; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; Institute for Clinical Evaluative Sciences; U.S. Department of Veterans Affairs","keywords":"Biomarker; Logistic regression; Maximization; Computer science; Data mining; Machine learning; Mathematics; Mathematical optimization; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009320758,0.0002674483,0.0007467582,0.0002872852,0.00004883264,0.00002091342,0.0001302395,0.0001387002,0.00006090598],"category_scores_gemma":[0.02280315,0.0002331328,0.00001268799,0.0003062225,0.0002503662,0.00002957937,0.0003105932,0.0003958697,0.000001913301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002038932,"about_ca_system_score_gemma":0.00007361418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001293339,"about_ca_topic_score_gemma":0.0002661482,"domain_scores_codex":[0.9977759,0.0003865964,0.0008733888,0.0004401606,0.0003188961,0.0002051125],"domain_scores_gemma":[0.9953851,0.003765728,0.0002895591,0.0001933584,0.0002990024,0.00006728806],"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":[0.00005360675,0.0001375333,0.005807503,0.003818777,0.0001287288,0.0001299699,0.009245455,0.00004270717,0.00005423818,0.9527308,0.002402592,0.02544811],"study_design_scores_gemma":[0.00110523,0.00004695048,0.01999238,0.001844953,0.00008111714,0.000001782879,0.0005620616,0.09770492,0.00001062577,0.8783762,0.00004453321,0.0002291744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001093332,0.0005015591,0.9946787,0.001854899,0.0005178857,0.0006101942,0.0001535008,0.00003470951,0.0005551912],"genre_scores_gemma":[0.1560694,0.001648004,0.8415655,0.0002648149,0.00005600976,0.0000934682,0.0002287002,0.00003681922,0.00003732218],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.154976,"threshold_uncertainty_score":0.9854282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.248377741755409,"score_gpt":0.4778237775230547,"score_spread":0.2294460357676457,"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."}}