{"id":"W2954707123","doi":"10.1002/sim.8281","title":"The Integrated Calibration Index (ICI) and related metrics for quantifying the calibration of logistic regression models","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":313,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; Institute of Health Services and Policy Research; Sunnybrook Hospital; University of Toronto","funders":"National Institute of Neurological Disorders and Stroke; National Institutes of Health; Ontario Ministry of Health and Long-Term Care; Canadian Institutes of Health Research; Patient-Centered Outcomes Research Institute; Heart and Stroke Foundation of Canada","keywords":"Calibration; Statistics; Percentile; Logistic regression; Mathematics; Range (aeronautics); Smoothing; Regression; Computer science","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00213575,0.0001456502,0.0003520928,0.0001079696,0.0001219727,0.00002416828,0.0001629847,0.0001050627,0.00004109528],"category_scores_gemma":[0.01684236,0.00006934835,0.00001701868,0.0004390411,0.0003415779,0.0000630884,0.00004171377,0.0002769512,3.157174e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003445659,"about_ca_system_score_gemma":0.00006078697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001449155,"about_ca_topic_score_gemma":0.00007036505,"domain_scores_codex":[0.9982336,0.0003063456,0.0007370912,0.0002000932,0.0003344023,0.0001884883],"domain_scores_gemma":[0.9826381,0.01647005,0.0003487299,0.0002789285,0.0002217455,0.00004242313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008500093,0.00002075999,0.0006365391,0.000182959,0.00001760534,0.000001397548,0.0007378232,0.0001689314,0.0003265337,0.9858239,0.001107258,0.01089129],"study_design_scores_gemma":[0.0004012694,0.0001349277,0.0003656265,0.0001770129,0.00002923034,0.000001511892,0.0005956407,0.5078098,0.00005090443,0.4903607,0.00002540589,0.00004802622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005599792,0.0002957331,0.9920734,0.0005499726,0.0003581065,0.0007081809,0.0001120803,0.00001599633,0.0002867017],"genre_scores_gemma":[0.8627844,0.0002434043,0.1365797,0.00005798993,0.00002926998,0.00002981876,0.00004731016,0.00002093622,0.0002071809],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8571846,"threshold_uncertainty_score":0.9914392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2038005309243087,"score_gpt":0.4336053912476601,"score_spread":0.2298048603233514,"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."}}