{"id":"W3016221674","doi":"10.1016/j.psychres.2020.112960","title":"Prediction of physical violence in schizophrenia with machine learning algorithms","year":2020,"lang":"en","type":"article","venue":"Psychiatry Research","topic":"Psychopathy, Forensic Psychiatry, Sexual Offending","field":"Psychology","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Machine learning; Random forest; Predictive power; Receiver operating characteristic; Artificial intelligence; Schizophrenia (object-oriented programming); Algorithm; Population; Statistical classification; Computer science; Documentation; Psychology; Medicine; Psychiatry","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":[0.002244782,0.0008905605,0.0007665072,0.001826468,0.0004442103,0.001060502,0.0008121174,0.001143412,0.001286205],"category_scores_gemma":[0.006271745,0.0002991171,0.0009618084,0.0006002005,0.0002946974,0.0006011807,0.000617208,0.001273699,0.0004386408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007324633,"about_ca_system_score_gemma":0.0009509071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009565374,"about_ca_topic_score_gemma":0.005931224,"domain_scores_codex":[0.9995258,0.0001876691,0.00006015492,0.00009186887,0.00005614942,0.00007839577],"domain_scores_gemma":[0.9952326,0.003716802,0.0002720556,0.0001331959,0.0004551978,0.0001900584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001649846,0.001079291,0.2619837,0.0001056702,0.00046661,0.0004173389,0.00006632684,0.5477785,0.0009955011,0.001027566,0.004427119,0.1800025],"study_design_scores_gemma":[0.00001638927,0.00006272381,0.004796427,0.00001132349,0.00002174898,0.00003197981,0.0000171301,0.9938193,0.0002037823,0.0009512563,0.00006244515,0.000005449573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8911693,0.002082944,0.1013495,0.001236364,0.000251755,0.0001453157,0.001458398,0.0008166258,0.001489881],"genre_scores_gemma":[0.9854757,0.0002400668,0.01256046,0.00007349129,0.00007833658,0.00004804702,0.0009036331,0.00001529204,0.0006048439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009565374,"threshold_uncertainty_score":0.01901942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08764488198443594,"score_gpt":0.3687078060430379,"score_spread":0.2810629240586019,"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."}}