{"id":"W3217141020","doi":"10.23889/ijpds.v6i1.1680","title":"Data Harmonization and Data Pooling from Cohort Studies: A Practical Approach for Data Management","year":2021,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Gestational Diabetes Research and Management","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Alberta Health Services; University of Calgary","funders":"","keywords":"Pooling; Harmonization; Matching (statistics); Computer science; Variable (mathematics); Construct (python library); Data mining; Sample (material); Econometrics; Data science; Statistics; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003331088,0.0001191866,0.0001850905,0.0002161431,0.0003663326,0.0006358256,0.003332434,0.00002769399,0.00002670595],"category_scores_gemma":[0.007890948,0.0001069486,0.00001486937,0.0002699823,0.0001318136,0.005192743,0.007965586,0.000144413,0.000003155382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001301317,"about_ca_system_score_gemma":0.0003259052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004127828,"about_ca_topic_score_gemma":0.00004055095,"domain_scores_codex":[0.996514,0.00004129278,0.0004664228,0.001217782,0.00149104,0.0002694337],"domain_scores_gemma":[0.9955125,0.0003328013,0.0002285179,0.002585595,0.001145812,0.0001947205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001433636,0.001926661,0.1151393,0.0009261002,0.007945925,0.0003613212,0.0002230912,0.001274116,0.001587855,0.03706806,0.5032619,0.3288521],"study_design_scores_gemma":[0.001350816,0.00003039248,0.04192725,0.0001090557,0.0003578431,0.00009203387,0.0005526646,0.8501382,0.00001766472,0.001815081,0.1034807,0.0001282811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004522294,0.001001873,0.9596987,0.01222182,0.001189019,0.001180404,0.01999741,0.00002311177,0.0001653313],"genre_scores_gemma":[0.05101548,0.002376674,0.67829,0.0006975921,0.0006795292,0.00002316496,0.266445,0.00001819642,0.0004543406],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8488641,"threshold_uncertainty_score":0.9928533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3638508337347413,"score_gpt":0.5330212202993609,"score_spread":0.1691703865646197,"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."}}