{"id":"W2337963257","doi":"10.21037/apm.2016.03.02","title":"Inter-rater reliability in performance status assessment among health care professionals: a systematic review","year":2016,"lang":"en","type":"review","venue":"Annals of Palliative Medicine","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Medicine; Inter-rater reliability; Rank correlation; Kappa; Cohen's kappa; Spearman's rank correlation coefficient; Performance status; MEDLINE; Family medicine; Specialty; Reliability (semiconductor); Internal medicine; Physical therapy; Cancer; Rating scale","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006840061,0.0008472031,0.008409712,0.0006447659,0.0003470043,0.000002262451,0.0005408068,0.0005280916,0.001000537],"category_scores_gemma":[0.004124311,0.0004598482,0.0003894065,0.0009204251,0.0003280036,0.0002201839,0.0002661711,0.002283397,0.0001546227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002152089,"about_ca_system_score_gemma":0.004216078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008835261,"about_ca_topic_score_gemma":0.0003743299,"domain_scores_codex":[0.9777333,0.01158645,0.007262127,0.0009271613,0.001212097,0.001278894],"domain_scores_gemma":[0.984323,0.004118032,0.007758046,0.001442881,0.001851756,0.0005063319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00001040304,0.00003758926,0.0535181,0.9095765,0.00009860575,0.000002453887,0.004275484,3.871284e-8,4.377486e-9,0.00005459928,0.005554035,0.02687223],"study_design_scores_gemma":[0.0004509795,0.0005230149,0.01729957,0.8991778,0.0002069932,2.803381e-7,0.002581377,0.000001924666,4.413906e-8,0.00001859253,0.07942655,0.0003128931],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001245077,0.9746947,0.00003968292,0.004378721,0.001351412,0.01820465,0.0004739168,0.00005936068,0.0006730809],"genre_scores_gemma":[0.0007715728,0.9877972,0.00007869023,0.003428715,0.0002162075,0.006556161,0.000504954,0.00008762501,0.0005588916],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.07387251,"threshold_uncertainty_score":0.9999127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3175021308731937,"score_gpt":0.6029644113554586,"score_spread":0.285462280482265,"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."}}