{"id":"W2413587883","doi":"10.1097/dss.0000000000000553","title":"A Randomized, Blinded Study to Validate the Merz Hand Grading Scale for Use in Live Assessments","year":2015,"lang":"en","type":"article","venue":"Dermatologic Surgery","topic":"Orthopedic Surgery and Rehabilitation","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Inter-rater reliability; Kappa; Medicine; Grading scale; Grading (engineering); Cohen's kappa; Randomized controlled trial; Physical therapy; Blinded study; Rating scale; Surgery; Psychology; Statistics; Mathematics","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":[0.03653821,0.002087187,0.003301382,0.000758237,0.001912947,0.001005164,0.001417015,0.002518316,0.007785345],"category_scores_gemma":[0.04099922,0.001407575,0.0009592016,0.0005349547,0.003272224,0.001791853,0.0012651,0.001808347,0.001534137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008560132,"about_ca_system_score_gemma":0.003515896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004316712,"about_ca_topic_score_gemma":0.0007837908,"domain_scores_codex":[0.9749457,0.01734688,0.0016576,0.002487573,0.002627321,0.0009350323],"domain_scores_gemma":[0.9608998,0.01821903,0.006445766,0.007384123,0.005026784,0.002024537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.7966787,0.1355506,0.01010586,0.0007461471,0.0005061261,0.0001511872,0.0008837627,0.0007039999,0.009774826,0.0005867825,0.001527151,0.04278487],"study_design_scores_gemma":[0.4261945,0.5611316,0.007432955,0.00007317599,0.0002465978,0.000103386,0.0001424365,0.001112115,0.001948494,0.0003764294,0.001189061,0.00004932032],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8942459,0.0004610113,0.008215657,0.0002080604,0.0008765477,0.09407155,0.0005176786,0.0001332376,0.001270346],"genre_scores_gemma":[0.8605565,0.0003010074,0.02994335,0.0007372422,0.0007220049,0.1056894,0.0004208017,0.00003548407,0.001594299],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03653821,"threshold_uncertainty_score":0.1932348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1576833898685142,"score_gpt":0.3798585321806786,"score_spread":0.2221751423121643,"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."}}