{"id":"W2329646725","doi":"10.1097/bpo.0000000000000557","title":"A Reliable and Valid Objective Structured Assessment of Technical Skill for the Application of a Pavlik Harness Based on International Expert Consensus","year":2015,"lang":"en","type":"article","venue":"Journal of Pediatric Orthopaedics","topic":"Hip disorders and treatments","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Medicine; Intraclass correlation; Delphi method; Reliability (semiconductor); Construct validity; Inter-rater reliability; Medical physics; Delphi; Medical education; Physical therapy; Surgery; Rating scale; Psychometrics; Artificial intelligence; Computer science; Statistics; Patient satisfaction; Clinical psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.02699031,0.0005025903,0.0007059466,0.004241593,0.00055121,0.000910937,0.0009327938,0.0006014996,0.001481254],"category_scores_gemma":[0.0460276,0.0002741113,0.0007910422,0.001004053,0.0009032187,0.001128172,0.002069389,0.0006946013,0.0004869885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004547,"about_ca_system_score_gemma":0.004241289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000649654,"about_ca_topic_score_gemma":0.001869303,"domain_scores_codex":[0.9740936,0.01055698,0.004433205,0.001396638,0.008940438,0.0005792388],"domain_scores_gemma":[0.945862,0.01332231,0.007108324,0.002732491,0.03006951,0.0009053671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009171585,0.001745523,0.4152594,0.002310768,0.0003335852,0.0006853103,0.01950543,0.004462303,0.03577613,0.002615354,0.008352054,0.5080369],"study_design_scores_gemma":[0.000502809,0.006495865,0.8774522,0.002361608,0.0004393094,0.002929149,0.02338909,0.03168658,0.02562093,0.004600645,0.02410459,0.0004172843],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8529426,0.0004918227,0.11665,0.0006120465,0.000202419,0.01162214,0.0009596702,0.0001920842,0.01632723],"genre_scores_gemma":[0.8180392,0.0003734659,0.1693708,0.0001613135,0.0000696374,0.009476776,0.001045063,0.00004006773,0.00142373],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02699031,"threshold_uncertainty_score":0.1427401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02206572355549037,"score_gpt":0.3454416523598861,"score_spread":0.3233759288043957,"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."}}