{"id":"W3165377967","doi":"10.5430/jha.v10n3p32","title":"A Comparison of statistical methods for hospital performance assessment","year":2021,"lang":"en","type":"article","venue":"Journal of Hospital Administration","topic":"Cardiac, Anesthesia and Surgical Outcomes","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medicine; Standardization; Benchmarking; Quality management; Ranking (information retrieval); Random effects model; Statistical significance; Statistics; Emergency medicine; Internal medicine; Operations management; Computer science; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005843347,0.0001030373,0.0007491094,0.0000467974,0.00003478627,0.00002353536,0.00004692687,0.00007098994,0.00005937898],"category_scores_gemma":[0.0005228131,0.00008093857,0.0003634925,0.00009176629,0.00005322463,0.0001196688,0.000009759519,0.0001702091,8.957315e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000558722,"about_ca_system_score_gemma":0.0005369766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.728146e-7,"about_ca_topic_score_gemma":2.405375e-7,"domain_scores_codex":[0.9986198,0.00008415086,0.0007288557,0.0001078159,0.0003315945,0.0001277792],"domain_scores_gemma":[0.9981651,0.0006146997,0.0003981818,0.0001091939,0.0005785872,0.0001341889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001199179,0.006243958,0.8889506,0.0007094279,0.0006772498,0.0004107187,0.0008627991,0.00002329021,0.004112777,0.02795567,0.00130195,0.06755234],"study_design_scores_gemma":[0.002944312,0.04488888,0.8900223,0.0001829767,0.0006976934,0.0004751358,0.001344986,0.001913657,0.04332967,0.0002584222,0.01371155,0.0002304294],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9058381,0.0002802617,0.08931973,0.002220846,0.0005334618,0.0002115855,0.000008335574,0.000005464523,0.001582201],"genre_scores_gemma":[0.8124175,0.00003699614,0.1871531,0.00003542218,0.0001597649,0.000004374945,0.0000228663,0.00000807747,0.0001619268],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09783337,"threshold_uncertainty_score":0.3300579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02815568240391402,"score_gpt":0.4457513695799683,"score_spread":0.4175956871760543,"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."}}