{"id":"W2892933709","doi":"10.1186/s13062-018-0223-8","title":"Predicting clinical outcomes in neuroblastoma with genomic data integration","year":2018,"lang":"en","type":"article","venue":"Biology Direct","topic":"Neuroblastoma Research and Treatments","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency","funders":"FP7 People: Marie-Curie Actions; European Commission","keywords":"Cluster analysis; Context (archaeology); Biology; Disease; Proportional hazards model; Machine learning; Cohort; Computational biology; Regression; Correlation; Computer science; Artificial intelligence; Bioinformatics; Data mining; Internal medicine; Statistics; Medicine; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002910866,0.0001143011,0.0002910738,0.0001096187,0.00004236092,0.0000077852,0.0001625194,0.00007706297,0.00003732209],"category_scores_gemma":[0.000569431,0.00006986127,0.00003142771,0.0001266791,0.0002481254,0.0000616662,0.0001505434,0.0001991162,0.0001168641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002863927,"about_ca_system_score_gemma":0.0001030608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001372599,"about_ca_topic_score_gemma":0.001136333,"domain_scores_codex":[0.9988064,0.0001793599,0.0002447322,0.0004374672,0.00007463579,0.000257474],"domain_scores_gemma":[0.9990051,0.0002663515,0.00005627268,0.0005250797,0.00004460141,0.0001025446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006311635,0.0002106735,0.9856726,0.000003279891,0.00007756859,0.00008160865,0.00001684982,5.178044e-8,0.00273305,0.00001139228,0.0001851987,0.01037658],"study_design_scores_gemma":[0.001895948,0.003313302,0.9923356,0.00003126162,0.00002956121,0.00005005483,0.00001018629,0.0004320112,0.0009903177,0.00001394699,0.0008395698,0.00005827298],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958088,0.00002231362,0.0000268388,0.0003711563,0.0001544896,0.0002999807,0.00003264956,0.00006837826,0.003215396],"genre_scores_gemma":[0.9985179,0.00002956069,0.0005917892,0.0002872713,0.0001750472,0.00001278729,0.0001004192,0.0000151113,0.0002700586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01031831,"threshold_uncertainty_score":0.284886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09325902072081434,"score_gpt":0.4139118766639032,"score_spread":0.3206528559430889,"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."}}