{"id":"W4415063342","doi":"10.1093/jamia/ocaf169","title":"Should we synthesize more than we need: impact of synthetic data generation for high-dimensional cross-sectional medical data","year":2025,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Public Health; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Deutsche Forschungsgemeinschaft","keywords":"Synthetic data; Medical research; Data collection; Big data; Data modeling","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","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007667142,0.0001885636,0.0005356917,0.00027389,0.0001979751,0.0002019168,0.03168564,0.0002357295,0.00003551266],"category_scores_gemma":[0.1719483,0.0001215949,0.0001829693,0.0008308305,0.000372003,0.001733059,0.03044821,0.0007986835,0.000002446468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006005439,"about_ca_system_score_gemma":0.001985811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009689355,"about_ca_topic_score_gemma":0.0000160328,"domain_scores_codex":[0.9943259,0.0002092499,0.001633987,0.0002384502,0.003257856,0.0003345229],"domain_scores_gemma":[0.9855528,0.003061001,0.003941867,0.006542839,0.0007036845,0.0001978101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000101311,0.0003421038,0.04864839,0.000121673,0.001160789,0.000005595097,0.0001498383,0.0006687974,0.0002280394,0.001300749,0.8753296,0.07194314],"study_design_scores_gemma":[0.0005654542,0.0001255273,0.02112817,0.0002581674,0.00006222456,0.00005286379,0.00005202733,0.9662448,0.0002619932,0.01065897,0.0004661303,0.0001236511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2492151,0.0001909632,0.5503424,0.1969358,0.002124893,0.0003434219,0.0007161617,0.00008897727,0.00004223449],"genre_scores_gemma":[0.8563432,0.0005755608,0.1409051,0.001516293,0.0004117585,0.000006938836,0.0001918444,0.00001522052,0.0000340771],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.965576,"threshold_uncertainty_score":0.9773933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06764900475797032,"score_gpt":0.3819244041408982,"score_spread":0.3142753993829279,"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."}}