{"id":"W3206292861","doi":"10.1177/0272989x211050909","title":"Model-Based ROC Curve: Examining the Effect of Case Mix and Model Calibration on the ROC Plot","year":2021,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Calibration; Plot (graphics); Smoothing; Receiver operating characteristic; Statistical model; Statistical hypothesis testing","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1397431,0.001903418,0.002064408,0.006556238,0.0008343458,0.004522728,0.003275085,0.003332174,0.004039856],"category_scores_gemma":[0.4195308,0.000641498,0.004799706,0.004754029,0.003098621,0.004079253,0.003764135,0.003553716,0.001018336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002829746,"about_ca_system_score_gemma":0.002517765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002674975,"about_ca_topic_score_gemma":0.001129563,"domain_scores_codex":[0.859817,0.1091534,0.005522888,0.01015664,0.01401949,0.001330534],"domain_scores_gemma":[0.3994468,0.5155538,0.02834137,0.03719058,0.01758659,0.001880896],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004867948,0.0007820028,0.3381537,0.002906079,0.008362968,0.0009572422,0.002166637,0.3155272,0.002858995,0.04208563,0.02319291,0.2581387],"study_design_scores_gemma":[0.000411659,0.002850032,0.1079765,0.0008901798,0.001781933,0.002469997,0.0006898715,0.8065251,0.005685635,0.057911,0.0123286,0.000479519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2348188,0.006658404,0.7345662,0.003760497,0.0005463089,0.001754562,0.003357311,0.00416419,0.01037378],"genre_scores_gemma":[0.894833,0.0005163752,0.100236,0.0006723739,0.000173718,0.0008942711,0.001616608,0.0006284523,0.0004289954],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8602569,"threshold_uncertainty_score":0.7390409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1178094628711977,"score_gpt":0.384155806512217,"score_spread":0.2663463436410194,"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."}}