{"id":"W4402464109","doi":"10.11159/icbes24.115","title":"Reducing Sample Selection Bias in Clinical Data through Generation of Multi-Objective Synthetic Data","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Nursing Research","keywords":"Computer science; Selection (genetic algorithm); Selection bias; Sample (material); Sampling bias; Synthetic data; Artificial intelligence; Data mining; Sample size determination; Statistics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.001754022,0.0001301053,0.000248845,0.0002355699,0.00009445445,0.0004101984,0.001440775,0.00004293361,1.099077e-7],"category_scores_gemma":[0.0003183058,0.00009350609,0.00002068255,0.001514276,0.0001286246,0.0009220529,0.0007617264,0.0002790967,1.573353e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000284615,"about_ca_system_score_gemma":0.00009579191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001561758,"about_ca_topic_score_gemma":0.000006255368,"domain_scores_codex":[0.9982246,0.00002121271,0.0004363704,0.0007893185,0.0003056416,0.0002228754],"domain_scores_gemma":[0.999011,0.0002979458,0.0001129143,0.0003810076,0.0001384086,0.00005872578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003703468,0.0004435581,0.006606348,0.001299468,0.0001454655,0.000005035374,0.001564792,0.05099378,0.02362762,0.6055748,0.002057205,0.3076448],"study_design_scores_gemma":[0.00009019016,0.00008180125,0.0008004446,0.0005737912,0.000007625214,0.00002015193,0.000003660823,0.9969112,0.001191001,0.00009062182,0.0001231409,0.0001063712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.196946,0.002069448,0.7974321,0.0002924878,0.002715671,0.0003439779,0.000014233,0.0001354496,0.00005064948],"genre_scores_gemma":[0.9812602,0.00008485623,0.01847916,0.00001459102,0.000127461,0.000004452447,7.212107e-7,0.000005997818,0.00002257573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9459174,"threshold_uncertainty_score":0.3955553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.121705373071728,"score_gpt":0.3260664809969761,"score_spread":0.2043611079252481,"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."}}