{"id":"W2346393506","doi":"10.1001/jamapsychiatry.2016.0316","title":"Prediction of Individual Response to Electroconvulsive Therapy via Machine Learning on Structural Magnetic Resonance Imaging Data","year":2016,"lang":"en","type":"article","venue":"JAMA Psychiatry","topic":"Electroconvulsive Therapy Studies","field":"Medicine","cited_by":276,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Electroconvulsive therapy; Magnetic resonance imaging; Major depressive disorder; Depression (economics); Psychology; Functional magnetic resonance imaging; Voxel; Medicine; Internal medicine; Nuclear medicine; Psychiatry; Radiology; Mood; Cognition","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007008738,0.0003020008,0.0004113909,0.0003002146,0.0001579963,0.0000215203,0.0004635162,0.00008466851,0.0001528791],"category_scores_gemma":[0.0003690607,0.0002055162,0.00007688889,0.0003743084,0.0001169417,0.0002046148,0.0001406655,0.0004246261,0.00002996822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009444127,"about_ca_system_score_gemma":0.0001641597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001995021,"about_ca_topic_score_gemma":0.00001701323,"domain_scores_codex":[0.9975598,0.0003041735,0.0004428782,0.0006469515,0.0005613354,0.0004848026],"domain_scores_gemma":[0.998307,0.0003019325,0.0001930615,0.0008835346,0.00018074,0.0001337355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.02669171,0.0001114192,0.3148381,0.00002413645,0.0001265901,0.000009721963,0.0006226029,7.486443e-7,0.3478229,0.00008650418,0.004900639,0.3047649],"study_design_scores_gemma":[0.01038368,0.007452832,0.93977,0.0004330747,0.00008393065,0.000139827,0.0001427707,0.0001364003,0.01939909,0.000539132,0.02122825,0.000290963],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9565698,0.01616041,0.0002510166,0.0252655,0.000385303,0.0008160037,0.0002430808,0.0001344672,0.0001744141],"genre_scores_gemma":[0.9931419,0.0005537138,0.001689646,0.003295092,0.0005622127,0.00004235698,0.00006605822,0.00006799449,0.0005809988],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6249319,"threshold_uncertainty_score":0.8380708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01935527744043775,"score_gpt":0.2819689065278576,"score_spread":0.2626136290874199,"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."}}