{"id":"W4399303408","doi":"10.1016/j.jclinepi.2024.111407","title":"The impact of an online course on agreement rates of the certainty of evidence assessment using Grading of Recommendations, Assessment, Development, and Evaluation Approach: a before-and-after study","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Ministério da Saúde; Hospital Moinhos de Vento","keywords":"Certainty; Medicine; Agreement; Statistics; Psychology; Mathematics; Linguistics","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":[0.3129922,0.001439277,0.007107151,0.002966639,0.001973278,0.00700988,0.003231406,0.005031697,0.006685773],"category_scores_gemma":[0.6746922,0.001780026,0.01638499,0.003510391,0.002243764,0.0103346,0.00522662,0.008028428,0.0008222367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004071406,"about_ca_system_score_gemma":0.006756049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004599397,"about_ca_topic_score_gemma":0.00488108,"domain_scores_codex":[0.6780063,0.2145932,0.05754621,0.01456373,0.03214344,0.003147118],"domain_scores_gemma":[0.1441427,0.7627493,0.04793876,0.0209859,0.02139049,0.002792808],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.1847395,0.01445603,0.2170728,0.03468162,0.1188682,0.0002724055,0.006253758,0.00385634,0.001219121,0.002489277,0.008604905,0.407486],"study_design_scores_gemma":[0.078344,0.07087988,0.4984628,0.02566579,0.242447,0.0007542119,0.004203318,0.04269903,0.005389151,0.01165799,0.0175768,0.001920102],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8573672,0.06206235,0.03565703,0.007988704,0.004253213,0.01653102,0.00499765,0.0009382267,0.01020469],"genre_scores_gemma":[0.9635524,0.002546309,0.02496859,0.001282262,0.0003741233,0.00547672,0.0007951057,0.0001794357,0.000825064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6870078,"threshold_uncertainty_score":0.8472029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9548444353446619,"score_gpt":0.751862279327699,"score_spread":0.2029821560169629,"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."}}