{"id":"W4294990764","doi":"10.1093/bjs/znac300","title":"Benchmarks in colorectal surgery: multinational study to define quality thresholds in high and low anterior resection","year":2022,"lang":"en","type":"article","venue":"British journal of surgery","topic":"Colorectal Cancer Surgical Treatments","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"","keywords":"Medicine; Percentile; Retrospective cohort study; Surgery; Colorectal cancer; Benchmarking; Quality management; Benchmark (surveying); Cancer; Internal medicine; Statistics; Operations management","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":[],"consensus_categories":[],"category_scores_codex":[0.003607092,0.0001282282,0.0008009293,0.0007268887,0.00009542722,0.0000387713,0.000057338,0.00003989694,0.0004819077],"category_scores_gemma":[0.001056622,0.0001499329,0.0001562384,0.0008422871,0.00003727058,0.0001708609,0.0001214615,0.0004814752,6.839685e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006452565,"about_ca_system_score_gemma":0.0002901724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002491286,"about_ca_topic_score_gemma":0.002979451,"domain_scores_codex":[0.9972147,0.0005057402,0.001023124,0.0002596215,0.0007314857,0.0002653707],"domain_scores_gemma":[0.998138,0.001183413,0.0002795698,0.00007285521,0.0001543873,0.0001718446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004539916,0.002341665,0.9637151,0.00003418648,0.00005393473,0.008075092,0.000226591,0.00004548307,0.0002198875,0.000001140583,0.0007136598,0.02003339],"study_design_scores_gemma":[0.002391906,0.0006616389,0.9917268,0.0004062398,0.00001631682,0.003955284,0.0005390804,0.0000160439,0.00006973393,0.00003007686,0.00005962054,0.0001272441],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974645,0.0009825726,9.314037e-7,0.000474065,0.0005674221,0.0004009311,0.00003799585,0.000007235263,0.00006437221],"genre_scores_gemma":[0.9993953,0.0002068572,0.00003780713,0.0001349229,0.00009772631,0.00006470278,0.00002444867,0.00001647102,0.00002173567],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02801176,"threshold_uncertainty_score":0.6114084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03375693130239583,"score_gpt":0.3116248784309254,"score_spread":0.2778679471285296,"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."}}