{"id":"W2558902621","doi":"10.1088/1741-2560/14/1/016002","title":"Prediction of antiepileptic drug treatment outcomes using machine learning","year":2016,"lang":"en","type":"article","venue":"Journal of Neural Engineering","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Machine learning; Antiepileptic drug; Support vector machine; Artificial intelligence; Random forest; Epilepsy; Computer science; Medicine; Psychiatry","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":[0.0002541165,0.0001329659,0.0002914404,0.0002434499,0.00004233583,0.00002171881,0.0002748555,0.00003099466,0.000006200835],"category_scores_gemma":[0.0002060379,0.00008096093,0.0001375962,0.0001651063,0.00001006861,0.0004322035,0.00005583654,0.0002013168,9.481753e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001447514,"about_ca_system_score_gemma":0.0000372215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004416021,"about_ca_topic_score_gemma":0.000001001956,"domain_scores_codex":[0.9988699,0.00006634412,0.000488637,0.000115097,0.0002701608,0.0001898467],"domain_scores_gemma":[0.9990575,0.0002217275,0.0003592633,0.0001656363,0.0001003619,0.00009549133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001571192,0.00005576108,0.4945508,0.00009562205,0.0000933874,0.00008412618,0.0006407571,0.4026229,0.07163466,0.0003286473,0.000007931573,0.02986968],"study_design_scores_gemma":[0.0006207229,0.0004331845,0.06597601,0.000182463,0.00001750826,0.0002817191,0.000006607163,0.9292853,0.002710288,0.00001456601,0.000381264,0.00009031724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8796018,0.0002648301,0.118565,0.0007273111,0.0007262449,0.00005131147,0.0000019107,0.00005535891,0.000006271767],"genre_scores_gemma":[0.9843207,0.00005028059,0.01543498,0.00001040937,0.0001090772,5.290947e-7,1.62823e-7,0.00001368723,0.00006018888],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5266625,"threshold_uncertainty_score":0.3301491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03211664052570933,"score_gpt":0.2624823863990266,"score_spread":0.2303657458733173,"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."}}