{"id":"W2909091936","doi":"10.3389/fpsyt.2018.00768","title":"Leveraging Machine Learning Approaches for Predicting Antidepressant Treatment Response Using Electroencephalography (EEG) and Clinical Data","year":2019,"lang":"en","type":"article","venue":"Frontiers in Psychiatry","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"National Institute of Mental Health; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Electroencephalography; Antidepressant; Psychology; Computer science; Machine learning; Artificial intelligence; Neuroscience; Psychiatry; Anxiety","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":[0.001328342,0.000229268,0.0003892386,0.0002773336,0.0003162619,0.00006028108,0.0003039804,0.00008592885,0.000002255146],"category_scores_gemma":[0.002540238,0.0002127127,0.00009914019,0.0003336438,0.0001558285,0.000331982,0.0002117227,0.0003237388,8.768166e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000742235,"about_ca_system_score_gemma":0.0001078988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003769093,"about_ca_topic_score_gemma":0.00002239766,"domain_scores_codex":[0.9973178,0.0005446931,0.0003824533,0.001144888,0.0001901846,0.0004199984],"domain_scores_gemma":[0.996744,0.002491724,0.0001747676,0.0005121816,0.00001370647,0.00006361221],"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":[0.001377152,0.0001754998,0.9925612,0.00003310444,0.00007001539,0.000002350623,0.0001626009,0.0008336696,0.0005160681,0.00004725559,0.0009331175,0.003287987],"study_design_scores_gemma":[0.003499846,0.001096494,0.297141,0.0001057262,0.00009713186,0.00003932671,0.001175176,0.6912524,0.0001679159,0.001263143,0.003763106,0.0003986931],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9762721,0.00213085,0.01394742,0.001276801,0.005433987,0.0007212358,0.00005356069,0.00008337254,0.00008067039],"genre_scores_gemma":[0.9670209,0.0002733757,0.03204208,0.0003547621,0.0001680727,0.00002343002,0.00001450567,0.00003634682,0.00006654176],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6954201,"threshold_uncertainty_score":0.8674172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09952798516227557,"score_gpt":0.3217194243755797,"score_spread":0.2221914392133041,"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."}}