{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1593972,0.0001951338,0.0006652804,0.00006426603,0.0002216889,0.00005663879,0.0002537596,0.0001644636,0.00002069984],"category_scores_gemma":[0.4282627,0.0001023086,0.0002173604,0.0003079433,0.0006238525,0.00114456,0.0003195724,0.0009979751,3.629636e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001453637,"about_ca_system_score_gemma":0.00118708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002697856,"about_ca_topic_score_gemma":0.00008260383,"domain_scores_codex":[0.9849476,0.005199512,0.007399026,0.000431303,0.001809345,0.0002132021],"domain_scores_gemma":[0.8376906,0.1337999,0.01440662,0.001101482,0.01278577,0.0002156012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.007814771,0.001415551,0.1488589,0.000518061,0.001476521,0.000009471632,0.001514985,0.0006326708,0.0001812162,0.0007306219,0.002596405,0.8342509],"study_design_scores_gemma":[0.01127831,0.003132127,0.9166011,0.0007917695,0.00884236,0.0002912259,0.01830892,0.02923163,0.00007851765,0.005129857,0.006134497,0.0001797172],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9291322,0.00179479,0.002944653,0.06202309,0.001135935,0.00246601,0.000006328757,0.000004315885,0.0004927298],"genre_scores_gemma":[0.7475219,0.007259027,0.2411671,0.003639227,0.0003489876,0.00003290648,0.00000170902,0.00001754321,0.00001159737],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8340712,"threshold_uncertainty_score":0.8655775,"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."}}