{"id":"W2073644162","doi":"10.1016/j.jclinepi.2008.10.009","title":"AMSTAR is a reliable and valid measurement tool to assess the methodological quality of systematic reviews","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1770,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Ottawa; Institute of Population and Public Health","funders":"","keywords":"Intraclass correlation; Inter-rater reliability; Kappa; Medicine; Construct validity; Reliability (semiconductor); Systematic review; Confidence interval; Criterion validity; Cohen's kappa; Medical physics; Statistics; Psychometrics; Mathematics; MEDLINE; Clinical psychology; Rating scale; Internal medicine; Biology","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":[0.3015169,0.002908503,0.01068659,0.03681651,0.001937943,0.005414873,0.002591542,0.003285479,0.01005835],"category_scores_gemma":[0.6635709,0.002386963,0.03081783,0.02307496,0.002468908,0.00608328,0.007409046,0.00349822,0.001347306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002959138,"about_ca_system_score_gemma":0.006340487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001572991,"about_ca_topic_score_gemma":0.005284213,"domain_scores_codex":[0.4932548,0.2099322,0.2071594,0.01212899,0.07596565,0.001558959],"domain_scores_gemma":[0.1330637,0.691256,0.1016426,0.0202521,0.05237325,0.001412229],"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":[0.0101038,0.0005399626,0.2644756,0.1240071,0.2092365,0.0004702116,0.003986549,0.004860072,0.002069441,0.009927721,0.04263671,0.3276864],"study_design_scores_gemma":[0.01512747,0.008353012,0.5670236,0.03611913,0.1850688,0.003451736,0.002744451,0.02700219,0.007666616,0.04168563,0.1035973,0.002160058],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1848566,0.1449367,0.4510584,0.0110706,0.00584417,0.05041367,0.1150721,0.007579149,0.02916872],"genre_scores_gemma":[0.4253428,0.012892,0.4675784,0.002529492,0.001341938,0.07150298,0.01564172,0.0009208599,0.002249824],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6984831,"threshold_uncertainty_score":0.861354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9935874369043814,"score_gpt":0.7700991734328491,"score_spread":0.2234882634715324,"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."}}