{"id":"W4210273173","doi":"10.1038/s41380-020-00892-3","title":"Identifying and validating subtypes within major psychiatric disorders based on frontal–posterior functional imbalance via deep learning","year":2020,"lang":"en","type":"article","venue":"Molecular Psychiatry","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal University Hospital; University of Saskatchewan; University of Alberta","funders":"National Science Fund for Distinguished Young Scholars; National Key Research and Development Program of China; China Medical University; Natural Science Foundation of Liaoning Province; National Natural Science Foundation of China","keywords":"Major depressive disorder; Bipolar disorder; Schizophrenia (object-oriented programming); White matter; Psychiatry; Biomarker; Medicine; Functional connectivity; Mini-international neuropsychiatric interview; Psychology; Clinical psychology; Neuroscience; Magnetic resonance imaging; Mood; Anxiety","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001867027,0.0003111602,0.0002474755,0.0001392369,0.0006235674,0.000132556,0.0001857352,0.00007199159,0.00006103201],"category_scores_gemma":[0.001306171,0.0003257788,0.0001363751,0.0005224084,0.0001066512,0.0001771987,0.0001169941,0.0004852427,0.00008093738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003573143,"about_ca_system_score_gemma":0.00005638139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001448895,"about_ca_topic_score_gemma":0.00004235956,"domain_scores_codex":[0.9975815,0.0002627314,0.0003071987,0.000983221,0.0005284903,0.0003368327],"domain_scores_gemma":[0.9989159,0.0004857372,0.0002046316,0.0002216753,0.00002876209,0.0001432933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001620628,0.0005380067,0.4243578,0.0007125366,0.0001552708,0.00007123355,0.001325727,0.03369251,0.523737,0.004352015,0.00183058,0.007606718],"study_design_scores_gemma":[0.01567083,0.005230767,0.3518958,0.0005081807,0.0005852489,0.0002816417,0.003236217,0.4948843,0.09641226,0.02170085,0.004252377,0.005341612],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8858688,0.0007741222,0.08525198,0.02351324,0.002472545,0.0004353721,0.000009871115,0.0003287108,0.001345348],"genre_scores_gemma":[0.9783691,0.000007500054,0.004932831,0.01633301,0.000213632,0.00003907675,0.000007978651,0.00006033921,0.00003655544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4611917,"threshold_uncertainty_score":0.9999194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01443363218190891,"score_gpt":0.2321950592787072,"score_spread":0.2177614270967983,"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."}}