{"id":"W3104912879","doi":"10.1093/jamia/ocaa249","title":"Optimizing the synthesis of clinical trial data using sequential trees","year":2020,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overfitting; Computer science; Metric (unit); Variable (mathematics); Data mining; Univariate; Clinical trial; Particle swarm optimization; Replicate; Machine learning; Similarity (geometry); Synthetic data; Artificial intelligence; Multivariate statistics; Statistics; Mathematics; 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":[0.008091546,0.00009727956,0.0005249904,0.0000534768,0.0001100936,0.0001168353,0.03085869,0.0001037946,0.000006297054],"category_scores_gemma":[0.292118,0.00005329406,0.0002056023,0.0006706478,0.0002734684,0.0009297901,0.02934195,0.000837134,0.000002003708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001203487,"about_ca_system_score_gemma":0.0005990746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002460237,"about_ca_topic_score_gemma":0.00000258551,"domain_scores_codex":[0.9953615,0.0005362541,0.001934596,0.00009533107,0.001873923,0.000198403],"domain_scores_gemma":[0.981896,0.003919183,0.009835723,0.003881427,0.0002919849,0.0001756414],"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":[0.00204562,0.0004553787,0.01124194,0.00009611111,0.001984608,0.00001998911,0.003081486,0.001862663,0.0002190207,0.00054167,0.4293559,0.5490956],"study_design_scores_gemma":[0.001995644,0.0001937906,0.0004038153,0.0000829666,0.0001019932,0.00001265744,0.0004230207,0.9944099,0.0002837088,0.0009467338,0.001067361,0.00007837048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3363371,0.00004099788,0.501573,0.1599361,0.001652094,0.0002319256,0.00003572946,0.00005939747,0.0001336519],"genre_scores_gemma":[0.6008103,0.0002843694,0.3949216,0.003215174,0.000754591,0.000001173719,0.00000202086,0.000009183929,0.000001584525],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9925473,"threshold_uncertainty_score":0.9785085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1580074542505678,"score_gpt":0.3968032561351933,"score_spread":0.2387958018846255,"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."}}