{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6167015,0.001694006,0.004918926,0.008335519,0.003591778,0.0109588,0.009886033,0.00325729,0.004652808],"category_scores_gemma":[0.7616795,0.002797664,0.004936261,0.01773471,0.01021148,0.008866803,0.01639203,0.005354093,0.0009206144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005961891,"about_ca_system_score_gemma":0.01918094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00706313,"about_ca_topic_score_gemma":0.007032031,"domain_scores_codex":[0.2536173,0.6312195,0.05758412,0.01720887,0.03735709,0.003013076],"domain_scores_gemma":[0.1361519,0.5608913,0.05831791,0.1978819,0.04451185,0.002245113],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003400626,0.0005361481,0.1730903,0.03060359,0.01264992,0.001189477,0.03422714,0.01557092,0.001878404,0.1680508,0.07205728,0.4867453],"study_design_scores_gemma":[0.001017696,0.001554114,0.120647,0.04756582,0.002926535,0.001861261,0.01546034,0.01479325,0.00443054,0.3473632,0.4414472,0.0009330273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09328596,0.0348682,0.6844566,0.1183573,0.009936954,0.01973539,0.01850923,0.00175838,0.01909202],"genre_scores_gemma":[0.3261582,0.006542491,0.5889591,0.02777209,0.003556526,0.03196879,0.01153638,0.001433033,0.002073317],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3832985,"threshold_uncertainty_score":0.4726754,"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."}}