{"id":"W2891356630","doi":"10.23889/ijpds.v3i4.868","title":"Harmonization of data from cohort studies– potential challenges and opportunities","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"","keywords":"Comparability; Harmonization; Missing data; Imputation (statistics); Computer science; Data quality; Statistics; Data mining; Mathematics; Engineering","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":[0.002888616,0.0000584496,0.0001170395,0.0001378104,0.0007179117,0.0001888616,0.001775287,0.00003156385,0.0000567751],"category_scores_gemma":[0.001707987,0.0000530819,0.00001244001,0.00007162274,0.0007029637,0.003848211,0.0005787378,0.00005230643,0.000001581312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007684698,"about_ca_system_score_gemma":0.0003174084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001848588,"about_ca_topic_score_gemma":0.002104487,"domain_scores_codex":[0.9982671,0.00006058877,0.0003421885,0.0002806523,0.0008714171,0.000178062],"domain_scores_gemma":[0.9980254,0.0001661772,0.0002834862,0.000327855,0.001074749,0.000122358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002064187,0.0001441714,0.09591192,0.00006774256,0.0004772332,0.00001618077,0.01308163,0.00002319115,0.0002424865,0.3575497,0.01840032,0.513879],"study_design_scores_gemma":[0.0008075048,0.00008944368,0.7207164,0.0003023143,0.0001168222,0.00003208904,0.02157563,0.02298763,0.00004991171,0.03356167,0.1994169,0.0003437233],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8176426,0.01412432,0.02935794,0.1011744,0.02779258,0.001046204,0.005971541,0.000095171,0.00279521],"genre_scores_gemma":[0.9702255,0.02143129,0.005685518,0.0004637899,0.001587381,0.00000139165,0.0004682456,0.000005010849,0.0001319082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6248044,"threshold_uncertainty_score":0.5521669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4731905228827818,"score_gpt":0.5105984239167461,"score_spread":0.0374079010339643,"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."}}