{"id":"W2953399894","doi":"10.1186/s12874-019-0769-x","title":"Ranking hospital performance based on individual indicators: can we increase reliability by creating composite indicators?","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Reliability (semiconductor); Ranking (information retrieval); Computer science; Reliability engineering; Statistics; Psychology; Medicine; Information retrieval; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.05770243,0.0003736537,0.001004781,0.001566545,0.001735403,0.00002023384,0.001185519,0.001397201,0.006326024],"category_scores_gemma":[0.09367735,0.0003200439,0.0001372966,0.001857776,0.0009254228,0.0001568935,0.000746472,0.007279112,0.0007769043],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001064134,"about_ca_system_score_gemma":0.006278801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003374929,"about_ca_topic_score_gemma":0.0002554233,"domain_scores_codex":[0.9337101,0.05702439,0.001517733,0.00117285,0.004490932,0.002083973],"domain_scores_gemma":[0.8791316,0.1170793,0.0005972121,0.001144365,0.0003909559,0.001656583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006048662,0.0001431078,0.9664741,0.001486553,0.00002409462,0.000007958699,0.002576321,0.00002026092,0.00005194003,0.0003540669,0.002787649,0.02546908],"study_design_scores_gemma":[0.004508093,0.002158841,0.9728236,0.002458118,0.00002484085,0.000003469496,0.003044038,0.005673833,0.000370368,0.0005230281,0.0079019,0.0005098708],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9847601,0.0001599132,0.00254708,0.00475039,0.001400233,0.002696593,0.000165789,0.0001962063,0.003323709],"genre_scores_gemma":[0.9779157,0.0001598617,0.01781164,0.002195559,0.0004464563,0.0008353746,0.0002586199,0.00007348727,0.000303274],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06005488,"threshold_uncertainty_score":0.9999251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2795359781563761,"score_gpt":0.5469929941505802,"score_spread":0.2674570159942041,"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."}}