{"id":"W2167922880","doi":"10.1111/j.1365-2753.2010.01561.x","title":"Evaluating clinical practice guidelines developed for the management of thyroid nodules and thyroid cancers and assessing the reliability and validity of the AGREE instrument","year":2011,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"CLARITY; Cronbach's alpha; Medicine; Intraclass correlation; Reliability (semiconductor); Validity; Medical physics; Clinical Practice; Clinical psychology; Family medicine; Psychometrics","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":[],"category_scores_codex":[0.1739982,0.0004983727,0.001429108,0.0083373,0.001060557,0.002357932,0.001628795,0.0012083,0.001117562],"category_scores_gemma":[0.3590341,0.0005720232,0.002014268,0.00528899,0.001495922,0.00265558,0.003958591,0.00130241,0.0002347781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003091907,"about_ca_system_score_gemma":0.009987369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003032214,"about_ca_topic_score_gemma":0.009365043,"domain_scores_codex":[0.8347837,0.08369751,0.04184567,0.003029668,0.03461777,0.002025729],"domain_scores_gemma":[0.5166322,0.2758634,0.09080582,0.01428607,0.09725793,0.005154517],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004726062,0.0008710812,0.7165613,0.005741903,0.001085402,0.0001803095,0.02744604,0.001575694,0.001336472,0.001656921,0.004677227,0.238395],"study_design_scores_gemma":[0.0004347397,0.003170144,0.9133939,0.006263789,0.0007425123,0.0006346198,0.0412534,0.007759687,0.002966153,0.003705813,0.01938054,0.00029472],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9634689,0.002651173,0.01664687,0.001683822,0.0001605499,0.006846601,0.001014891,0.0001235137,0.007403607],"genre_scores_gemma":[0.9073868,0.001280385,0.0832783,0.0003994364,0.00005763115,0.005942524,0.001233559,0.00002306542,0.0003982931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8260018,"threshold_uncertainty_score":0.9202017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6845993376729306,"score_gpt":0.645858508235771,"score_spread":0.03874082943715962,"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."}}