{"id":"W4416946695","doi":"10.21203/rs.3.rs-8206381/v1","title":"Evaluating the Clinical Competence of Artificial Intelligence Applications in Psychiatry: A Systematic Review","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Children's Hospital of Eastern Ontario","funders":"","keywords":"Applications of artificial intelligence; Psychosocial; Test (biology); Competence (human resources); Intervention (counseling); Systematic review; MEDLINE","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03097235,0.001320553,0.01036819,0.00703666,0.0009538452,0.004289913,0.002174184,0.002681987,0.002582014],"category_scores_gemma":[0.1507831,0.001378806,0.01160531,0.006742055,0.002345538,0.00336615,0.002653558,0.002294011,0.0002629832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005953902,"about_ca_system_score_gemma":0.01862088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01220208,"about_ca_topic_score_gemma":0.03568089,"domain_scores_codex":[0.9715903,0.01270197,0.00931829,0.001628483,0.00432032,0.0004405933],"domain_scores_gemma":[0.8578021,0.1133334,0.01773255,0.002285083,0.007575932,0.001271018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.001407749,0.0001017798,0.003409364,0.889957,0.05157902,0.00007103079,0.0005358746,0.0001860697,0.0001884917,0.0002602873,0.000993095,0.05131025],"study_design_scores_gemma":[0.002313076,0.0008511388,0.01124093,0.7271934,0.2491275,0.0002027717,0.0007935465,0.0002501073,0.0003323108,0.0005332829,0.007067584,0.00009441827],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.007663913,0.9894351,0.0004217297,0.0004035699,0.0001874047,0.00121515,0.0002886842,0.00001465131,0.0003698333],"genre_scores_gemma":[0.111991,0.8822007,0.002771095,0.0008974175,0.0001474576,0.001529618,0.0003092077,0.00001507058,0.0001383675],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.03097235,"threshold_uncertainty_score":0.1637994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4966492805009045,"score_gpt":0.6741392047330237,"score_spread":0.1774899242321192,"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."}}