{"id":"W7005446084","doi":"","title":"Quality assessment of observational studies in a drug-safety systematic review, comparison of two tools: the Newcastle–Ottawa Scale and the RTI item bank","year":2014,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Inter-rater reliability; Statistic; Percentile; Scale (ratio); Cohen's kappa; Observational study; Quality (philosophy); Quality assessment","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.454024,0.003018549,0.02072247,0.0307359,0.003211347,0.008767817,0.006592719,0.004180919,0.003049857],"category_scores_gemma":[0.6871713,0.00333214,0.03399456,0.02783331,0.006720946,0.008530753,0.01084607,0.004067793,0.0004820357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01226655,"about_ca_system_score_gemma":0.02528136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008891839,"about_ca_topic_score_gemma":0.02306242,"domain_scores_codex":[0.2447595,0.310964,0.3635276,0.02116556,0.05717911,0.002404212],"domain_scores_gemma":[0.1869383,0.5493281,0.1500694,0.03730649,0.07275622,0.003601538],"domain_codex":"reporting","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"observational","study_design_scores_codex":[0.005426349,0.0001846243,0.09932937,0.6431766,0.1470515,0.0003010584,0.00914541,0.002056835,0.0008575767,0.004019847,0.01113416,0.07731677],"study_design_scores_gemma":[0.01724762,0.004783089,0.2771002,0.3785493,0.2264254,0.001458984,0.009645806,0.01456923,0.002716798,0.02070519,0.04401951,0.002778823],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1433283,0.4997553,0.1075849,0.01988126,0.005812352,0.165314,0.04788077,0.001452357,0.008990873],"genre_scores_gemma":[0.4477,0.03780611,0.2187524,0.002949776,0.0009557378,0.2789923,0.01172415,0.0002949407,0.0008245114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5459759,"threshold_uncertainty_score":0.6732855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9354791294795641,"score_gpt":0.7453040008931215,"score_spread":0.1901751285864426,"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."}}