{"id":"W3010261457","doi":"10.1001/jama.2020.1230","title":"Validation and Utility Testing of Clinical Prediction Models","year":2020,"lang":"en","type":"article","venue":"JAMA","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"","keywords":"Medicine; Otorhinolaryngology; Family medicine; Neurology; MEDLINE; Psychiatry; Law","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01085901,0.00007297593,0.0005473131,0.00005179625,0.00005652657,0.00003154019,0.00008639768,0.0001238049,0.00007168442],"category_scores_gemma":[0.01379648,0.00009504338,0.00005411598,0.000119973,0.00004896922,0.0005393248,0.00003987674,0.0001330147,0.00009984423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003136143,"about_ca_system_score_gemma":0.00005991285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001908307,"about_ca_topic_score_gemma":0.000002607115,"domain_scores_codex":[0.995959,0.0002114006,0.00331317,0.0003421013,0.00005214807,0.0001221542],"domain_scores_gemma":[0.9971314,0.001020095,0.001464118,0.0001842352,0.0000778197,0.0001223081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004257308,0.00008368604,0.9365247,0.0005305399,0.00004798357,2.422842e-7,0.001901233,0.0009278644,0.000009470197,0.03266324,0.01715227,0.01011623],"study_design_scores_gemma":[0.0010082,0.0001312985,0.2898499,0.00003920777,0.000006550394,0.00000111681,0.0002508367,0.680938,0.00002445398,0.02148598,0.00614768,0.0001167768],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9422191,0.0003728876,0.02143092,0.02637172,0.0002507071,0.0003427839,0.0002937929,0.00005516061,0.008662877],"genre_scores_gemma":[0.9884549,0.00003792937,0.006497746,0.004503634,0.0004362666,0.0000109813,0.00001879602,0.000009897751,0.00002979775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6800102,"threshold_uncertainty_score":0.9945107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7255774010685754,"score_gpt":0.4801200022781392,"score_spread":0.2454573987904362,"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."}}