{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12979,0.0001391703,0.001371581,0.001006713,0.00004497339,0.00001055307,0.0002006105,0.00009722961,0.00005771733],"category_scores_gemma":[0.04939642,0.0001107269,0.00006871263,0.0005482315,0.00006328936,0.0001682042,0.00001302058,0.0001574942,0.00001150927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000334258,"about_ca_system_score_gemma":0.0002905259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002122344,"about_ca_topic_score_gemma":0.003462197,"domain_scores_codex":[0.9928098,0.001665956,0.00472586,0.0003767766,0.0002089551,0.000212602],"domain_scores_gemma":[0.99143,0.006526295,0.00157125,0.0003484683,0.00008088228,0.00004311276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001748188,0.0002741537,0.9058133,0.00245567,0.00007237457,0.000001183865,0.001726311,0.0002931748,0.00001353998,0.05261872,0.03256554,0.00399124],"study_design_scores_gemma":[0.003303247,0.0002909707,0.9692701,0.002388434,0.00002836693,0.000001441415,0.001886977,0.001055253,0.000009455082,0.01383212,0.007778713,0.0001549036],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.100889,0.0944278,0.001435745,0.7980061,0.0008373085,0.003160601,0.00007035889,0.00001770434,0.001155313],"genre_scores_gemma":[0.987484,0.003936728,0.0003836773,0.007645198,0.0001707275,0.0003456228,0.000007544413,0.000006504046,0.00001993912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.886595,"threshold_uncertainty_score":0.9586109,"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."}}