{"id":"W2168654307","doi":"10.1186/gm385","title":"Exploiting the noise: improving biomarkers with ensembles of data analysis methodologies","year":2012,"lang":"en","type":"article","venue":"Genome Medicine","topic":"Lung Cancer Treatments and Mutations","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"National Institutes of Health; Center for Translational Molecular Medicine; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Biomarker; Medicine; Hazard ratio; Confidence interval; Biomarker discovery; Oncology; Personalized medicine; Bioinformatics; Internal medicine; Computer science; 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":[],"consensus_categories":[],"category_scores_codex":[0.0009558059,0.0001232508,0.0003925053,0.0001884781,0.00009376602,0.000003924555,0.0001835153,0.00002893729,0.0001539909],"category_scores_gemma":[0.0002590481,0.00005639909,0.00004471186,0.0007136283,0.0002132241,0.0001357797,0.00009296031,0.00007305618,0.000002449782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004735334,"about_ca_system_score_gemma":0.00006667616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007405771,"about_ca_topic_score_gemma":0.00004302819,"domain_scores_codex":[0.9989691,0.00007118616,0.0002544294,0.0002063157,0.0002548601,0.0002441414],"domain_scores_gemma":[0.9984683,0.000369359,0.000175437,0.0008069708,0.00008380449,0.00009614445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006599404,0.0003036401,0.5733324,0.0006437041,0.02796941,0.00004691052,0.02078908,0.0001114989,0.1717768,0.0006638542,0.001036758,0.2026661],"study_design_scores_gemma":[0.004431684,0.000983169,0.8970074,0.0002311831,0.04216971,0.0001220902,0.03984525,0.0004167033,0.00368503,0.0000656406,0.01073303,0.0003091416],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8490038,0.02676477,0.1020102,0.01159265,0.000260077,0.001068069,0.0001182186,0.0001258741,0.00905633],"genre_scores_gemma":[0.9710551,0.0001247311,0.02774601,0.0002372803,0.0002974493,0.00002103076,0.0002794618,0.00001421966,0.0002247455],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.323675,"threshold_uncertainty_score":0.2299888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.146234176021666,"score_gpt":0.4128145628081334,"score_spread":0.2665803867864674,"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."}}