{"id":"W2605897081","doi":"10.1186/s41512-017-0012-3","title":"Validation of prediction models: examining temporal and geographic stability of baseline risk and estimated covariate effects","year":2017,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Covariate; Baseline (sea); Stability (learning theory); Statistics; Econometrics; Computer science; Mathematics; Machine learning; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1938306,0.0008487805,0.001119624,0.0018155,0.001232772,0.002064947,0.002616382,0.001547056,0.0007394753],"category_scores_gemma":[0.3966152,0.0007244663,0.002076548,0.002507091,0.002788673,0.003016446,0.003348582,0.002190442,0.0001462808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001642278,"about_ca_system_score_gemma":0.002814705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0177146,"about_ca_topic_score_gemma":0.01095454,"domain_scores_codex":[0.8815401,0.1052797,0.003287277,0.006399221,0.002678204,0.0008155163],"domain_scores_gemma":[0.4270358,0.5178553,0.02114617,0.02666483,0.00638303,0.0009149051],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001198117,0.0001774162,0.7869083,0.0001636987,0.004405241,0.0003777292,0.001315086,0.1573466,0.0006243684,0.007544541,0.0005520891,0.03938681],"study_design_scores_gemma":[0.0002663141,0.0006853018,0.2165841,0.0001613711,0.0006654733,0.0003601251,0.00104238,0.7528195,0.001410319,0.02429209,0.001621258,0.00009173146],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6788971,0.0009209386,0.3166277,0.001050027,0.00007073402,0.000234953,0.0006243901,0.0002306277,0.001343555],"genre_scores_gemma":[0.9766617,0.0000876972,0.0220817,0.00008560673,0.00003334157,0.0001234067,0.0007522373,0.0000348681,0.0001395],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8061694,"threshold_uncertainty_score":0.9941504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3648981795435242,"score_gpt":0.4617530783644725,"score_spread":0.09685489882094833,"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."}}