{"id":"W1602160603","doi":"10.1186/1471-2288-14-137","title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Traumatic Brain Injury and Neurovascular Disturbances","field":"Medicine","cited_by":796,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Support vector machine; Logistic regression; Statistics; Random forest; Sample size determination; Artificial intelligence; Receiver operating characteristic; Regression; Machine learning; Computer science; 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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05033034,0.0002117726,0.0008361284,0.0003191176,0.0003105988,0.00003474902,0.0008635205,0.0003412737,0.00009315325],"category_scores_gemma":[0.1315216,0.0001680368,0.0001290141,0.0003367706,0.0003834299,0.0001439085,0.000508283,0.001044426,0.000008594636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005162588,"about_ca_system_score_gemma":0.0004131757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009384075,"about_ca_topic_score_gemma":0.0002157569,"domain_scores_codex":[0.986476,0.008905104,0.0007256467,0.001070129,0.002063147,0.0007599543],"domain_scores_gemma":[0.9360024,0.06087084,0.0001916165,0.00185032,0.0004950863,0.0005896917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007146961,0.003970191,0.05061894,0.003897286,0.000752394,0.0001600463,0.005250841,0.004778277,0.001196188,0.001731724,0.001587665,0.9189095],"study_design_scores_gemma":[0.002194774,0.001576476,0.002516148,0.0003666143,0.0001263259,0.00004128459,0.0009037263,0.9807326,0.000739442,0.007844724,0.002802164,0.0001557004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1651945,0.0003182104,0.8311675,0.0004132254,0.00015155,0.002180387,0.00001876243,0.0001900678,0.000365739],"genre_scores_gemma":[0.830259,0.00004966712,0.1680567,0.0002576195,0.0007598153,0.0003779563,0.00008288941,0.00004800345,0.0001083922],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9759544,"threshold_uncertainty_score":0.9778848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7132462483034406,"score_gpt":0.5762959983442477,"score_spread":0.1369502499591929,"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."}}