{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2744204,0.001765052,0.002551091,0.008866024,0.0009954021,0.005038444,0.002655539,0.002055398,0.00347495],"category_scores_gemma":[0.4392105,0.001019779,0.00570824,0.009136173,0.002537661,0.004287874,0.003998967,0.005350468,0.0008899795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005796011,"about_ca_system_score_gemma":0.007339011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004081017,"about_ca_topic_score_gemma":0.003241754,"domain_scores_codex":[0.6097493,0.3196731,0.01598166,0.009406893,0.04381052,0.001378522],"domain_scores_gemma":[0.3132485,0.6063178,0.01787692,0.0238495,0.03717612,0.001531173],"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":[0.003460751,0.0007088093,0.05583629,0.004234191,0.007927406,0.0001243212,0.002456195,0.0353618,0.001027889,0.09998455,0.02059611,0.7682817],"study_design_scores_gemma":[0.00250107,0.008240898,0.1425297,0.01043473,0.003422809,0.001020981,0.004291368,0.4765916,0.004390634,0.2448483,0.1004567,0.001271256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04629005,0.02104308,0.9043025,0.006181038,0.001891409,0.003551869,0.00288818,0.002091758,0.01176002],"genre_scores_gemma":[0.2186918,0.008301062,0.7586577,0.001461565,0.0008052714,0.007076428,0.002389993,0.001044189,0.001571934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7255796,"threshold_uncertainty_score":0.8947688,"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."}}