{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007047997,0.00007600564,0.0001233542,0.0001290761,0.00004954272,0.0001251423,0.00144666,0.00002611739,0.00002250287],"category_scores_gemma":[0.0005052969,0.00007629036,0.0000107212,0.0002206411,0.000008091869,0.000879159,0.0003780416,0.0001179549,0.000004626349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008941562,"about_ca_system_score_gemma":0.0003623178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00273496,"about_ca_topic_score_gemma":0.001292473,"domain_scores_codex":[0.9977314,0.0006388816,0.0004130464,0.0006196349,0.0004155842,0.0001814631],"domain_scores_gemma":[0.9975702,0.0003740721,0.0001475728,0.001782448,0.00007574819,0.00005000043],"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":[0.000004848664,0.00006757963,0.05040731,0.00210902,0.00001753482,0.000002437069,0.006066553,0.006170771,0.0001496822,0.003250384,0.000258662,0.9314952],"study_design_scores_gemma":[0.0001784552,0.00007202043,0.02060122,0.0004592329,0.000007525213,0.000002746969,0.00008907116,0.9771456,0.00005153489,0.001226673,0.0001018254,0.00006412053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1515269,0.0003187907,0.841367,0.004862384,0.0005655717,0.0007255238,0.000515989,0.00009981881,0.00001796936],"genre_scores_gemma":[0.9691866,0.00001053733,0.02920358,0.0001706839,0.00006449341,0.00002819588,0.001321685,0.00001129759,0.000002927781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9709748,"threshold_uncertainty_score":0.413446,"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."}}