{"id":"W4214525197","doi":"10.1192/bjp.2022.28","title":"Using polygenic scores and clinical data for bipolar disorder patient stratification and lithium response prediction: machine learning approach","year":2022,"lang":"en","type":"article","venue":"The British Journal of Psychiatry","topic":"Bipolar Disorder and Treatment","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Movement Disorders; McGill University; Douglas Mental Health University Institute; McGill University Health Centre; Dalhousie University; Montreal Neurological Institute and Hospital","funders":"NIH Clinical Center; Agence Nationale de la Recherche; Deutsche Forschungsgemeinschaft; U.S. Department of Veterans Affairs; Canadian Institutes of Health Research; Grantová Agentura České Republiky","keywords":"Bipolar disorder; Major depressive disorder; Population stratification; Schizophrenia (object-oriented programming); Psychology; Lithium (medication); Clinical psychology; Statistics; Machine learning; Artificial intelligence; Psychiatry; Computer science; Cognition; Mathematics; Single-nucleotide polymorphism; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00944061,0.001190221,0.001296845,0.002331379,0.0004734813,0.001072582,0.0009303205,0.001060098,0.001122598],"category_scores_gemma":[0.01584108,0.0004125308,0.001462615,0.001574608,0.0005519565,0.0005733269,0.0007944782,0.001639844,0.0003504478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005879346,"about_ca_system_score_gemma":0.0009896773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008879635,"about_ca_topic_score_gemma":0.008813345,"domain_scores_codex":[0.9961682,0.003006118,0.0001416622,0.0004230652,0.0001329144,0.000128023],"domain_scores_gemma":[0.9867336,0.01111398,0.0007263324,0.0007230185,0.000494278,0.0002087381],"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":[0.0009956514,0.0007421653,0.619517,0.00009238929,0.002023895,0.0004513781,0.0003652129,0.2294546,0.001494174,0.001113737,0.001500442,0.1422494],"study_design_scores_gemma":[0.00005611621,0.0002640268,0.05551811,0.00003626495,0.0001710204,0.000133219,0.0000788678,0.9395503,0.0003075098,0.003611305,0.0002344844,0.00003865848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8607616,0.000781536,0.1351734,0.001087252,0.0000480196,0.0001604949,0.000887797,0.0003907961,0.0007091253],"genre_scores_gemma":[0.9734284,0.0001000562,0.02524631,0.000097024,0.00004506363,0.0000730601,0.0007257437,0.00001782482,0.0002665313],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00944061,"threshold_uncertainty_score":0.04992735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04624303011947828,"score_gpt":0.3203143575729224,"score_spread":0.2740713274534441,"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."}}