{"id":"W3215495292","doi":"10.1016/j.jclinepi.2021.11.024","title":"GRADE concept paper 2: Concepts for judging certainty on the calibration of prognostic models in a body of validation studies","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Impact; Ted Rogers Centre for Heart Research","funders":"British Heart Foundation","keywords":"Certainty; Inference; Calibration; Econometrics; Computer science; Medicine; Statistics; Artificial intelligence; Mathematics","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":[0.01302665,0.00009381092,0.001670001,0.00006438509,0.00002585941,0.000001976272,0.0000947061,0.0001350485,0.00001928746],"category_scores_gemma":[0.1989399,0.00005421558,0.0003865543,0.0001084217,0.0003856741,0.00007058182,0.00002816819,0.0007004706,1.228509e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002417045,"about_ca_system_score_gemma":0.0002502647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007989419,"about_ca_topic_score_gemma":0.000001465509,"domain_scores_codex":[0.9940051,0.00253247,0.002960571,0.0001566113,0.0001765466,0.0001686582],"domain_scores_gemma":[0.9425548,0.05472899,0.002009167,0.0001576609,0.0004576268,0.00009172917],"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":[0.002617079,0.001931692,0.6793957,0.0008887597,0.001788886,0.0001349781,0.002796535,0.1270429,0.006264937,0.1340803,0.009480731,0.03357749],"study_design_scores_gemma":[0.01023914,0.004433943,0.1340941,0.003345955,0.0006926259,0.0001621884,0.002106715,0.6787232,0.003112139,0.161817,0.001060795,0.0002122706],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8884524,0.001343412,0.04217913,0.06715737,0.0005282264,0.0002799217,0.000003210534,0.000003607545,0.0000526878],"genre_scores_gemma":[0.9888142,0.0007809917,0.005565737,0.004453282,0.000344807,0.000006250775,0.00000574487,0.000009179625,0.0000197965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5516802,"threshold_uncertainty_score":0.8078078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2834012222335031,"score_gpt":0.5316164983690372,"score_spread":0.2482152761355341,"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."}}