{"id":"W2103899236","doi":"10.1136/bmjopen-2012-001368","title":"Inter-rater and test–retest reliability of quality assessments by novice student raters using the Jadad and Newcastle–Ottawa Scales","year":2012,"lang":"en","type":"article","venue":"BMJ Open","topic":"Electroconvulsive Therapy Studies","field":"Medicine","cited_by":208,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Health Sciences; McMaster University","funders":"","keywords":"Jadad scale; Intraclass correlation; Medicine; Inter-rater reliability; Reliability (semiconductor); Test (biology); Observational study; Clinical psychology; Rating scale; Physical therapy; Randomized controlled trial; Psychometrics; Psychology; Internal medicine; Developmental psychology","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":[0.4689955,0.001476591,0.005842799,0.01200985,0.002127904,0.004426314,0.00304965,0.001874637,0.002707701],"category_scores_gemma":[0.6325096,0.001744027,0.00973557,0.01127394,0.003973044,0.004567989,0.005422732,0.002534125,0.00100021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004364891,"about_ca_system_score_gemma":0.007833662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002638734,"about_ca_topic_score_gemma":0.004346377,"domain_scores_codex":[0.4074023,0.2846763,0.2229961,0.02231142,0.06073934,0.001874595],"domain_scores_gemma":[0.1859823,0.4594086,0.13003,0.04538113,0.1771467,0.002051236],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01470202,0.00085266,0.3062472,0.1858939,0.0435622,0.0004384105,0.03837071,0.003949855,0.009062398,0.006944678,0.02994864,0.3600273],"study_design_scores_gemma":[0.006755535,0.008794844,0.6899464,0.08965393,0.03093262,0.001756648,0.01012182,0.01730293,0.01659859,0.02171666,0.1039344,0.002485655],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3088985,0.108134,0.35593,0.007764257,0.00518864,0.1614759,0.02685467,0.002442967,0.0233111],"genre_scores_gemma":[0.5027177,0.01184539,0.3124746,0.001266829,0.0007330388,0.160995,0.007510599,0.0005675374,0.001889253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5310044,"threshold_uncertainty_score":0.6548231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1192619632601358,"score_gpt":0.5071182900183459,"score_spread":0.3878563267582101,"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."}}