{"id":"W2319227677","doi":"10.1097/nci.0b013e31822db44e","title":"When and How to Evaluate Interrater Reliability of Patient Assessment Tools","year":2011,"lang":"en","type":"article","venue":"AACN Advanced Critical Care","topic":"Intensive Care Unit Cognitive Disorders","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Icon; Inter-rater reliability; Citation; Download; Medicine; Grey literature; Library science; MEDLINE; Computer science; Psychology; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.3109966,0.001243634,0.003750021,0.008982609,0.003837081,0.01112518,0.003475643,0.005203599,0.01545305],"category_scores_gemma":[0.6639124,0.001859083,0.002577993,0.004899151,0.004514445,0.01173275,0.005078302,0.003637682,0.02003263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004510452,"about_ca_system_score_gemma":0.01019986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004483538,"about_ca_topic_score_gemma":0.0115658,"domain_scores_codex":[0.6942682,0.2052027,0.04664439,0.006414651,0.0446846,0.002785564],"domain_scores_gemma":[0.3817591,0.3618906,0.03029623,0.03470941,0.1854606,0.005883988],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007917586,0.0002653855,0.01577636,0.006783191,0.0005167303,0.0002887438,0.01294483,0.0005351049,0.001963132,0.004717924,0.400897,0.5545199],"study_design_scores_gemma":[0.001914922,0.001623986,0.08891486,0.06031063,0.001649141,0.002126136,0.03601211,0.01290545,0.02741805,0.0577551,0.7072515,0.002118237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09252895,0.05952604,0.2676038,0.2380589,0.04165952,0.06905945,0.01492873,0.01098922,0.2056455],"genre_scores_gemma":[0.3196194,0.02722981,0.5312908,0.01633226,0.006545326,0.06733134,0.004942161,0.004237647,0.02247127],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6890033,"threshold_uncertainty_score":0.8496639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03938211208478479,"score_gpt":0.3527617728504692,"score_spread":0.3133796607656844,"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."}}