{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1832757,0.003909288,0.004672512,0.01942184,0.00331241,0.01739764,0.008610987,0.01035777,0.01258819],"category_scores_gemma":[0.5420246,0.001929259,0.006469831,0.00896654,0.01162542,0.01741959,0.01282652,0.01365553,0.003241477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005427958,"about_ca_system_score_gemma":0.009307313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003089504,"about_ca_topic_score_gemma":0.001815595,"domain_scores_codex":[0.8420134,0.09414634,0.01581354,0.01101516,0.03471192,0.002299623],"domain_scores_gemma":[0.4323805,0.422844,0.03223943,0.03666363,0.06956267,0.006309838],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001124674,0.0002172698,0.01581356,0.007523801,0.002195684,0.0003188831,0.001785159,0.01824372,0.001041797,0.493344,0.0829994,0.3753921],"study_design_scores_gemma":[0.0003336238,0.0007208618,0.004328877,0.004337574,0.0009263944,0.0007654888,0.0003604912,0.0238619,0.002156244,0.8947114,0.06721715,0.0002799552],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008326895,0.01503533,0.9210106,0.0268056,0.005968723,0.001403097,0.00318415,0.0008230151,0.01744263],"genre_scores_gemma":[0.2913456,0.007631608,0.6574374,0.01530111,0.01229479,0.004858483,0.004456847,0.0008855531,0.005788564],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8167243,"threshold_uncertainty_score":0.969266,"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."}}