{"id":"W2762658547","doi":"10.1001/jama.2017.12126","title":"Discrimination and Calibration of Clinical Prediction Models","year":2017,"lang":"en","type":"article","venue":"JAMA","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1650,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Toronto General Hospital; Impact; University Health Network","funders":"","keywords":"Medicine; Calibration; Event (particle physics); Predictive modelling; Machine learning; Data mining; Artificial intelligence; Medical physics; Statistics; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08998592,0.001577415,0.001416984,0.004712642,0.0009155946,0.006591436,0.002358259,0.003205011,0.007210467],"category_scores_gemma":[0.4530614,0.001043608,0.001678179,0.004323266,0.002199733,0.005002911,0.004459563,0.004475591,0.003752099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002745595,"about_ca_system_score_gemma":0.003501856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006270405,"about_ca_topic_score_gemma":0.003536535,"domain_scores_codex":[0.933148,0.04835178,0.003165048,0.003093903,0.01127743,0.0009638991],"domain_scores_gemma":[0.7411227,0.2079744,0.009398394,0.0187877,0.02149198,0.001224981],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000862792,0.0003285539,0.09890047,0.0007007403,0.0005124262,0.0002659551,0.001614476,0.1472695,0.0004459,0.1374761,0.08739477,0.5242283],"study_design_scores_gemma":[0.0001877804,0.0004323051,0.02871037,0.001922631,0.000237887,0.0006909204,0.0006746881,0.6967105,0.002435845,0.2209823,0.04672232,0.0002924403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07000806,0.007339616,0.830848,0.01635829,0.001574882,0.001258846,0.004222554,0.003773762,0.06461596],"genre_scores_gemma":[0.6590023,0.003661368,0.320731,0.003098163,0.0006042712,0.001482942,0.003931057,0.001054726,0.006434185],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9100141,"threshold_uncertainty_score":0.4758967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5712920549782778,"score_gpt":0.4924409180879964,"score_spread":0.07885113689028145,"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."}}