{"id":"W2996818987","doi":"10.1001/jamanetworkopen.2019.18377","title":"Use of Machine Learning for Predicting Escitalopram Treatment Outcome From Electroencephalography Recordings in Adult Patients With Depression","year":2020,"lang":"en","type":"article","venue":"JAMA Network Open","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; Baycrest Hospital; St. Michael's Hospital; Simon Fraser University; McGill University; Queen's University; McMaster University; University Health Network; University of Toronto; Centre for Addiction and Mental Health; University of British Columbia; St. Joseph’s Healthcare Hamilton; Kingston General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Escitalopram; Electroencephalography; Depression (economics); Psychology; Outcome (game theory); Audiology; Neuroscience; Psychiatry; Medicine; Hippocampus","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001117752,0.0001844244,0.0003358982,0.00004542246,0.0001227523,0.0002241994,0.0004444777,0.00005867522,0.00001062531],"category_scores_gemma":[0.0003888074,0.0001316353,0.0000649002,0.0003879735,0.00003377126,0.0006248419,0.0002228944,0.0002014714,0.000001300321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002951999,"about_ca_system_score_gemma":0.00001445941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007460994,"about_ca_topic_score_gemma":0.000191154,"domain_scores_codex":[0.998419,0.0001649262,0.0003721903,0.0005365936,0.0001719235,0.0003353053],"domain_scores_gemma":[0.9986629,0.0007563577,0.0002894762,0.0001480353,0.00005203901,0.00009121057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001133973,0.0001030361,0.9741152,0.000009886828,0.00001799744,0.000004042369,0.0007359551,0.007545425,0.0009738068,0.0000102485,0.0001481177,0.01520231],"study_design_scores_gemma":[0.00838475,0.005271936,0.6860486,0.0007736403,0.00006308533,0.000001619402,0.0001002618,0.2726621,0.02344954,0.000152434,0.002564046,0.0005280377],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970644,0.00002399214,0.001247327,0.0003873895,0.0001004028,0.0009973767,0.00004651981,0.00004667086,0.00008595169],"genre_scores_gemma":[0.9935449,0.0000187942,0.005336349,0.0008443575,0.0001029724,0.00005687114,0.00004591791,0.00002508867,0.00002474084],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2880666,"threshold_uncertainty_score":0.5367932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04068721537967242,"score_gpt":0.2700226085828117,"score_spread":0.2293353932031393,"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."}}