{"id":"W4405212503","doi":"10.1016/j.jclinepi.2024.111639","title":"Defining decision thresholds for judgments on health benefits and harms using the grading of recommendations assessment, development, and evaluation (GRADE) evidence to decision (EtD) frameworks: a randomized methodological study (GRADE-THRESHOLD)","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; McMaster University Medical Centre; Impact; McMaster University","funders":"","keywords":"Grading (engineering); Categorization; Guideline; Medicine; Evidence-based medicine; Actuarial science; Psychology; Management science; Alternative 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.53139,0.003535601,0.009876007,0.02256621,0.003572362,0.01051672,0.009168345,0.009697796,0.006068519],"category_scores_gemma":[0.7626328,0.002786311,0.02023313,0.01396254,0.006723323,0.0109015,0.009032777,0.0116894,0.001469724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01279152,"about_ca_system_score_gemma":0.02159159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005442165,"about_ca_topic_score_gemma":0.007826734,"domain_scores_codex":[0.3143729,0.4716736,0.1538643,0.009811396,0.0480911,0.002186731],"domain_scores_gemma":[0.2261828,0.5579301,0.07446998,0.02719686,0.1104958,0.003724451],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.0135452,0.001113224,0.02997111,0.2158374,0.03197826,0.0003265061,0.01013118,0.01038115,0.002364194,0.09069131,0.09231868,0.5013417],"study_design_scores_gemma":[0.02388972,0.006912216,0.03063118,0.2724841,0.05857574,0.001072785,0.007178041,0.05302345,0.01473164,0.3384653,0.1900794,0.002956364],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0336688,0.09746874,0.5753437,0.03368781,0.01096695,0.2016512,0.01414274,0.001724713,0.0313454],"genre_scores_gemma":[0.1201131,0.008868712,0.7449707,0.005694149,0.000492057,0.116579,0.002535844,0.0002669274,0.0004796685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.46861,"threshold_uncertainty_score":0.5778795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.902069972364624,"score_gpt":0.6969552872768768,"score_spread":0.2051146850877472,"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."}}