{"id":"W4396754825","doi":"10.2196/55118","title":"Comparison of Synthetic Data Generation Techniques for Control Group Survival Data in Oncology Clinical Trials: Simulation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Random forest; Cart; Clinical trial; Medicine; Bayesian probability; Computer science; Regression; Machine learning; Oncology; Medical physics; Artificial intelligence; Statistics; Internal medicine; Engineering; Mathematics; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03658542,0.000139955,0.0008869327,0.0001978937,0.00005260968,0.0001193856,0.002616324,0.0003155488,0.00001829483],"category_scores_gemma":[0.01525078,0.0001098489,0.00005407192,0.0003228934,0.00008248531,0.0009862265,0.00102979,0.000738523,0.000006490777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000644515,"about_ca_system_score_gemma":0.0005034035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004467158,"about_ca_topic_score_gemma":0.0002238819,"domain_scores_codex":[0.9925535,0.002295911,0.00359383,0.0003913395,0.0009185695,0.0002467928],"domain_scores_gemma":[0.984306,0.01278479,0.0006096222,0.002015001,0.0001235144,0.0001610866],"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":[0.00005938728,0.0009210188,0.01225597,0.000546624,0.00006005025,0.000006151161,0.004087076,0.0008505351,0.000001722565,0.002907533,0.002818069,0.9754859],"study_design_scores_gemma":[0.000877818,0.0009180917,0.0008171429,0.0001258303,0.00002774982,0.000002033439,0.0004309922,0.9812725,0.000001471856,0.0001249106,0.01530176,0.00009971709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01118035,0.0001064601,0.9832429,0.001637125,0.001171232,0.00228991,0.00008503773,0.0002008358,0.00008615304],"genre_scores_gemma":[0.9600656,0.00001660706,0.03868383,0.0002334137,0.0004405952,0.0000995396,0.0004479873,0.000009793008,0.000002632176],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.980422,"threshold_uncertainty_score":0.9930442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4320630988531221,"score_gpt":0.6101241499769695,"score_spread":0.1780610511238474,"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."}}