{"id":"W2990787575","doi":"10.3390/diagnostics9040219","title":"A Hierarchical Machine Learning Model to Discover Gleason Grade-Specific Biomarkers in Prostate Cancer","year":2019,"lang":"en","type":"article","venue":"Diagnostics","topic":"Cancer, Lipids, and Metabolism","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Prostate cancer; Medicine; Prostate; Cohort; Disease; Oncology; Feature selection; Grading (engineering); Cancer; Artificial intelligence; Machine learning; Internal medicine; Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001728262,0.0008741203,0.000851261,0.001630924,0.0005038955,0.0006505821,0.001517573,0.0008500597,0.001571914],"category_scores_gemma":[0.00333303,0.0003257528,0.00128308,0.001025343,0.0003825797,0.0005664844,0.0006599211,0.00117246,0.0006725871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001310174,"about_ca_system_score_gemma":0.001439691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02490263,"about_ca_topic_score_gemma":0.02346863,"domain_scores_codex":[0.9994445,0.0001974464,0.00003387401,0.0001431608,0.00008932548,0.0000916756],"domain_scores_gemma":[0.9987207,0.0007857306,0.0001184273,0.00008133568,0.0002284902,0.00006531679],"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":[0.0004803698,0.0003382007,0.03674722,0.0001829772,0.0003726567,0.0002179743,0.0001824141,0.7881004,0.002635566,0.004358802,0.007692693,0.1586908],"study_design_scores_gemma":[0.00000897799,0.00002633559,0.001153364,0.000006768643,0.00001901235,0.00001171566,0.000005379291,0.996333,0.000132706,0.002094228,0.0002035009,0.000004974495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3207831,0.003120545,0.6610103,0.002152742,0.000242253,0.0004701644,0.005255214,0.002892314,0.004073267],"genre_scores_gemma":[0.9042539,0.0004809924,0.08798867,0.0003649462,0.0001622197,0.0003141095,0.003507368,0.00007398414,0.002853821],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02490263,"threshold_uncertainty_score":0.04951537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01110716034245409,"score_gpt":0.258108087133157,"score_spread":0.2470009267907029,"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."}}