{"id":"W2417098700","doi":"10.1016/j.jclinepi.2016.05.007","title":"Geographic and temporal validity of prediction models: different approaches were useful to examine model performance","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Computer science; Predictive modelling; Statistics; Machine learning; Mathematics","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":[0.01554694,0.0001723114,0.001499219,0.0002010999,0.0000562846,0.000006659338,0.000682571,0.0002754763,0.000003947632],"category_scores_gemma":[0.009597832,0.0000968014,0.0002765161,0.0001144973,0.0002032736,0.0003850588,0.000295277,0.0006772586,0.000001247676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002492213,"about_ca_system_score_gemma":0.000111656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001267048,"about_ca_topic_score_gemma":0.000007481575,"domain_scores_codex":[0.9928764,0.002874248,0.003252845,0.0003989088,0.0002672872,0.0003303043],"domain_scores_gemma":[0.9876379,0.009184521,0.002055858,0.0004789553,0.000222367,0.0004203385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009799171,0.00008872319,0.936217,0.00005821929,0.00002679294,0.000001380083,0.00005392366,0.0108034,0.000007720588,0.004081495,0.0001703548,0.04839297],"study_design_scores_gemma":[0.0003823417,0.001170565,0.4962088,0.0001025874,0.000009614141,0.0000306721,0.000002319974,0.4883339,0.000004956327,0.01361942,0.00007662374,0.00005813428],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5573383,0.0001017332,0.435399,0.006728947,0.0003174555,0.00007359946,0.000004091216,0.00001386439,0.00002302208],"genre_scores_gemma":[0.9516674,0.0009503048,0.04657098,0.0004887159,0.0002824189,0.000004024526,6.262744e-7,0.000008418104,0.00002711807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4775305,"threshold_uncertainty_score":0.9987447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4903653697627472,"score_gpt":0.4388877148245395,"score_spread":0.05147765493820777,"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."}}