{"id":"W4409642815","doi":"10.1136/bmjebm-2024-113171","title":"Challenges in the selection and measurement of outcomes in psychiatric trials","year":2025,"lang":"en","type":"article","venue":"BMJ evidence-based medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"Danmarks Frie Forskningsfond","keywords":"Selection (genetic algorithm); Psychiatry; Psychology; Medicine; Computer science; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8256297,0.002121339,0.01400384,0.01313898,0.004269548,0.02315521,0.01126709,0.01124341,0.003464327],"category_scores_gemma":[0.9448464,0.003714228,0.00667528,0.01950479,0.01986462,0.0172214,0.01349452,0.02258771,0.001743556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01287098,"about_ca_system_score_gemma":0.03057786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0125518,"about_ca_topic_score_gemma":0.01443737,"domain_scores_codex":[0.08867963,0.7653288,0.09537622,0.009380509,0.03909361,0.002141162],"domain_scores_gemma":[0.01804242,0.9220448,0.01979847,0.01463267,0.02395604,0.001525517],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00320954,0.000791259,0.0792201,0.03309648,0.015036,0.0005083747,0.008476363,0.01299446,0.0004774149,0.1566003,0.1202542,0.5693356],"study_design_scores_gemma":[0.002699286,0.001169628,0.04886525,0.03934029,0.004256661,0.001036347,0.004121182,0.03189278,0.00102269,0.789652,0.07512131,0.0008226305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.02076721,0.1393474,0.2360535,0.5680715,0.01437876,0.005436067,0.004284083,0.0004649863,0.01119652],"genre_scores_gemma":[0.4430617,0.04514427,0.342404,0.1130103,0.02711192,0.02447266,0.002789891,0.0007054493,0.001299817],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1743703,"threshold_uncertainty_score":0.2150297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7992621237512433,"score_gpt":0.5470442325903778,"score_spread":0.2522178911608655,"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."}}