{"id":"W1974057428","doi":"10.1177/0163278707307924","title":"Assessment of Family Physicians' Performance Using Patient Charts","year":2007,"lang":"en","type":"article","venue":"Evaluation & the Health Professions","topic":"Healthcare Quality and Management","field":"Health Professions","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Association des Médecins d'Urgence du Québec","funders":"","keywords":"Chart; Medicine; Inter-rater reliability; Recall; Concordance; Medical record; Reliability (semiconductor); Cohen's kappa; Family medicine; Psychology; Statistics; Rating scale","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.02303459,0.0002031432,0.0004203795,0.0001940928,0.00337293,0.00000478316,0.0002573306,0.0001639235,0.0002899207],"category_scores_gemma":[0.0002421613,0.0001456294,0.00008464073,0.0006371916,0.00009992249,0.0001876356,0.0002118462,0.0009940572,0.00006424569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105465,"about_ca_system_score_gemma":0.00330965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007384409,"about_ca_topic_score_gemma":0.0002033704,"domain_scores_codex":[0.9903169,0.004971887,0.00186187,0.0003552841,0.001495302,0.0009987337],"domain_scores_gemma":[0.9958805,0.0008397636,0.00147118,0.000750449,0.0008525203,0.0002056026],"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":[0.0002456249,0.001291298,0.05378916,0.005457427,0.0001634718,0.000001825365,0.1316383,0.001501641,0.002221373,0.03665697,0.02824578,0.7387872],"study_design_scores_gemma":[0.001474689,0.0005566836,0.8419961,0.003080551,0.00007822247,6.246112e-7,0.09015826,0.03039747,0.00006287033,0.000935908,0.03096384,0.0002947558],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9495943,0.0003094324,0.01172987,0.01932334,0.003381027,0.0071634,0.00002575495,0.00009415956,0.008378726],"genre_scores_gemma":[0.980508,0.0001493809,0.002415508,0.01573557,0.0003019872,0.0003948865,0.00004358169,0.00003014289,0.0004209135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7882069,"threshold_uncertainty_score":0.9979246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4189002070409529,"score_gpt":0.6045903599396676,"score_spread":0.1856901528987147,"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."}}