{"id":"W4389061858","doi":"10.1200/cci.23.00116","title":"Evaluating the Utility and Privacy of Synthetic Breast Cancer Clinical Trial Data Sets","year":2023,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; McMaster University; Alberta Health Services; Ottawa Hospital; University of Ottawa; Agricultural Research Institute of Ontario","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institutes of Health Research; Government of Ontario","keywords":"Computer science; Synthetic data; Data sharing; Generative model; Clinical trial; Data mining; Data type; Breast cancer; Machine learning; Artificial intelligence; Generative grammar; Medicine; Cancer; Alternative medicine","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":[0.01460538,0.0002336179,0.0006667122,0.00008700309,0.0001988339,0.0001876511,0.03097983,0.00031225,0.00005175804],"category_scores_gemma":[0.07574285,0.0001581434,0.0001425126,0.0009247743,0.0008953437,0.001213333,0.1154631,0.000970176,0.00003285623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004299279,"about_ca_system_score_gemma":0.0007402556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000123923,"about_ca_topic_score_gemma":0.00003866503,"domain_scores_codex":[0.9945071,0.0004868063,0.002999569,0.0005791062,0.0009209855,0.000506393],"domain_scores_gemma":[0.9770527,0.005890934,0.001245982,0.01541698,0.0002400156,0.0001533867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006795459,0.0001038252,0.01997359,0.0001489092,0.00009770781,0.000001678592,0.000213573,0.00001950406,7.06129e-7,0.0002097798,0.1217567,0.8567945],"study_design_scores_gemma":[0.005221759,0.0002691102,0.04903531,0.0001543817,0.0000707646,0.00000660463,0.00008855716,0.9271248,0.000006398504,0.01418947,0.003628046,0.0002048294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9184826,0.000388303,0.01086325,0.06071075,0.004967406,0.00166637,0.001612049,0.0009895337,0.0003197241],"genre_scores_gemma":[0.859369,0.008847631,0.128078,0.002512571,0.0007614185,0.0002379915,0.0001018705,0.00004374357,0.00004778145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9271052,"threshold_uncertainty_score":0.974263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5048688417325166,"score_gpt":0.5517641226211488,"score_spread":0.04689528088863226,"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."}}