{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.05789609,0.0001104438,0.0004660777,0.00005548149,0.0001875146,0.002118612,0.008854667,0.00004974246,0.00042565],"category_scores_gemma":[0.03995207,0.00008422801,0.00005108284,0.0003814039,0.00005435321,0.001485209,0.01695548,0.00009007742,0.0001253241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001632891,"about_ca_system_score_gemma":0.0006685727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008191967,"about_ca_topic_score_gemma":0.005955818,"domain_scores_codex":[0.993495,0.001932288,0.001469047,0.001570087,0.001320328,0.0002132373],"domain_scores_gemma":[0.9867384,0.002839098,0.0004649841,0.009598044,0.0002439536,0.0001154978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.009349477,0.002684507,0.001290391,0.00002179175,0.000168517,0.00005535458,0.0005915348,0.000002797979,0.000002705318,0.004588807,0.8325784,0.1486657],"study_design_scores_gemma":[0.03917745,0.001238234,0.002915755,0.0000483101,0.0002807855,0.000005087345,0.0126572,0.006867401,0.00001899725,0.01211846,0.9242839,0.000388373],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3140984,0.00004039963,0.03406288,0.1971376,0.01688208,0.2959386,0.05875337,0.0003004235,0.0827862],"genre_scores_gemma":[0.7517543,0.00008031743,0.06257853,0.01139222,0.005132528,0.01253687,0.06252386,0.0001461835,0.09385513],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4376559,"threshold_uncertainty_score":0.9989173,"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."}}