{"id":"W3155972762","doi":"10.1136/bmjopen-2020-043497","title":"Can synthetic data be a proxy for real clinical trial data? A validation study","year":2021,"lang":"en","type":"article","venue":"BMJ Open","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; McGill University Health Centre; Children's Hospital of Eastern Ontario; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Univariate; Medicine; Bivariate analysis; Multivariate statistics; Metric (unit); Synthetic data; Statistic; Multivariate analysis; Data mining; Proxy (statistics); Statistics; Internal medicine; Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4236102,0.001466364,0.001434584,0.002357542,0.001281329,0.005941331,0.0048625,0.003685094,0.005029719],"category_scores_gemma":[0.7506392,0.00101512,0.003573605,0.003396764,0.007642843,0.005010446,0.00460442,0.004451626,0.001194132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002017104,"about_ca_system_score_gemma":0.004548281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001717948,"about_ca_topic_score_gemma":0.0008428556,"domain_scores_codex":[0.5724742,0.3858261,0.01319419,0.01124914,0.0159313,0.001325098],"domain_scores_gemma":[0.1157077,0.6707475,0.04122232,0.1527074,0.01827912,0.001335798],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.02159517,0.0035938,0.5904657,0.007187559,0.01613818,0.001133534,0.008186401,0.08355308,0.003412079,0.06980944,0.02527191,0.1696532],"study_design_scores_gemma":[0.01025026,0.01893471,0.2481439,0.008576185,0.00585616,0.004315289,0.004319897,0.4037983,0.01082797,0.172764,0.111351,0.0008623995],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4945783,0.009431945,0.4540893,0.00970206,0.002203152,0.00779295,0.01135814,0.001034368,0.009809803],"genre_scores_gemma":[0.9244804,0.0005071929,0.06146732,0.003062682,0.0003094768,0.004434535,0.005078013,0.0002093222,0.0004510972],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5763898,"threshold_uncertainty_score":0.7107913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8969700184148548,"score_gpt":0.6912436001651321,"score_spread":0.2057264182497227,"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."}}