{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02322933,0.0009288047,0.0007663885,0.0009933349,0.0005215793,0.001207274,0.001549814,0.001356307,0.001032442],"category_scores_gemma":[0.06230785,0.0004727722,0.0008216258,0.0006453813,0.001881646,0.001130123,0.002506343,0.002346567,0.0002090875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009843967,"about_ca_system_score_gemma":0.001072519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001714037,"about_ca_topic_score_gemma":0.002218694,"domain_scores_codex":[0.9932796,0.005186659,0.0001863493,0.0006888988,0.0005075946,0.0001508013],"domain_scores_gemma":[0.9303417,0.05759211,0.004171543,0.005024283,0.002170276,0.000700089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005648761,0.0002337791,0.03953725,0.0002474317,0.0002332568,0.000327401,0.0006242858,0.868867,0.002607184,0.02622968,0.003415236,0.05711263],"study_design_scores_gemma":[0.00005317232,0.0001379962,0.002935138,0.00006180698,0.00002859866,0.0001038757,0.00006940695,0.9661212,0.001871438,0.02733408,0.001255028,0.0000282967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1691455,0.0005220137,0.8251153,0.001974756,0.0001979833,0.0004433545,0.0007526359,0.0003785162,0.001469905],"genre_scores_gemma":[0.8697853,0.0002436959,0.1261317,0.0008024885,0.0001488908,0.0004511643,0.001535742,0.00008613933,0.0008149039],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02322933,"threshold_uncertainty_score":0.1228499,"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."}}