{"id":"W3177409267","doi":"10.1007/s00464-021-08604-w","title":"Guideline Assessment Project II: statistical calibration informed the development of an AGREE II extension for surgical guidelines","year":2021,"lang":"en","type":"article","venue":"Surgical Endoscopy","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Reliability (semiconductor); Medicine; Guideline; Scope (computer science); Medical physics; MEDLINE; Quality (philosophy); Computer science; Pathology","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":[0.4430571,0.001250877,0.001765364,0.006568592,0.004592978,0.009366078,0.005049176,0.004652232,0.01848275],"category_scores_gemma":[0.6483538,0.002521989,0.003422784,0.006664612,0.003488299,0.006149386,0.01534325,0.01121226,0.005509449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008483498,"about_ca_system_score_gemma":0.08895209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00797105,"about_ca_topic_score_gemma":0.01452128,"domain_scores_codex":[0.6428397,0.2576709,0.03829514,0.007984133,0.04741579,0.005794234],"domain_scores_gemma":[0.218341,0.4177006,0.04522772,0.08697177,0.2173077,0.01445123],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003679551,0.005086295,0.05463778,0.00695622,0.001198302,0.0004341483,0.0197445,0.008352123,0.003169049,0.05497334,0.2635481,0.5782206],"study_design_scores_gemma":[0.006494787,0.006220212,0.1118883,0.01931099,0.002044203,0.000632547,0.01422595,0.03974108,0.01699941,0.08029845,0.7013578,0.0007862677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1096697,0.001093971,0.4650558,0.06671967,0.004151721,0.2185241,0.03262502,0.007474576,0.09468539],"genre_scores_gemma":[0.0769363,0.000266548,0.7709952,0.00609357,0.0003556559,0.1308017,0.00827853,0.001057534,0.005215056],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5569429,"threshold_uncertainty_score":0.6868098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2640234877397016,"score_gpt":0.543832347289486,"score_spread":0.2798088595497845,"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."}}