{"id":"W4392302553","doi":"10.1016/j.patter.2024.100946","title":"An evaluation of synthetic data augmentation for mitigating covariate bias in health data","year":2024,"lang":"en","type":"article","venue":"Patterns","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; CHEO Research Institute; Compute Canada","keywords":"Covariate; Statistics; Computer science; Econometrics; Health data; Data science; Mathematics; Economics; Health care","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01611488,0.0008224819,0.000712035,0.0007225805,0.0003407578,0.0007680034,0.001334325,0.0009437055,0.000713351],"category_scores_gemma":[0.04787033,0.0002067836,0.0005969603,0.000673994,0.0009212813,0.0009619568,0.001238437,0.0008180715,0.0001670207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004692636,"about_ca_system_score_gemma":0.001059738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001886633,"about_ca_topic_score_gemma":0.001541346,"domain_scores_codex":[0.9947411,0.00392661,0.0001979994,0.0004727953,0.0005351374,0.0001263199],"domain_scores_gemma":[0.9605928,0.030852,0.001752702,0.003776854,0.002565089,0.0004606241],"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":[0.003771798,0.0008490438,0.03505506,0.0007175907,0.0005068023,0.0002810006,0.0005928126,0.6881488,0.008912694,0.006561491,0.005873635,0.2487293],"study_design_scores_gemma":[0.000124858,0.0007887552,0.003504701,0.00006926587,0.00005633902,0.0001502211,0.000114946,0.9817207,0.006593035,0.005027648,0.001826391,0.00002306726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5283381,0.002100287,0.4610263,0.001600133,0.0004662449,0.0005814338,0.001272234,0.002163992,0.002451233],"genre_scores_gemma":[0.8265911,0.0002550157,0.1704948,0.0003405828,0.0001070308,0.0002740748,0.001375524,0.00007501645,0.0004868794],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01611488,"threshold_uncertainty_score":0.08522463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4298372440353359,"score_gpt":0.5011297922777481,"score_spread":0.07129254824241227,"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."}}