{"id":"W2143844589","doi":"10.1093/ije/dyq139","title":"Quality, quantity and harmony: the DataSHaPER approach to integrating data across bioclinical studies","year":2010,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":181,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; University of Toronto; University of British Columbia; The Quebec Population Health Research Network; McGill University; University of Ottawa; Ontario Institute for Cancer Research; Université de Montréal","funders":"Wellcome Trust","keywords":"Harmonization; Biobank; Pooling; Standardization; Documentation; Data science; Data quality; Data collection; General partnership; Multidisciplinary approach; Management science; Computer science; Knowledge management; Political science; Business; Engineering; Sociology; Social science; Bioinformatics; Marketing; Biology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01996573,0.0001327641,0.0003797994,0.00003354529,0.0001496184,0.00002717152,0.001551653,0.0000881499,0.0001229666],"category_scores_gemma":[0.03466809,0.00008142256,0.00005591424,0.00006599403,0.0008659827,0.0004063606,0.002259142,0.0008898318,0.00006937699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007280718,"about_ca_system_score_gemma":0.00002070273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005279904,"about_ca_topic_score_gemma":0.0008528414,"domain_scores_codex":[0.99692,0.0009254784,0.001069223,0.0004605365,0.0003287923,0.000295945],"domain_scores_gemma":[0.9933268,0.005298286,0.0006392903,0.000503273,0.00005933037,0.0001730593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008117505,0.0001533087,0.9068072,0.000005754057,0.0002077856,0.00001252029,0.001142126,0.0001199243,0.003425477,0.00299756,0.01400635,0.0710408],"study_design_scores_gemma":[0.0004735444,0.00009236496,0.9132053,0.00002892217,0.00002152462,0.0003385838,0.001606214,0.001876515,0.00004373039,0.003856854,0.07827862,0.0001778643],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9585264,0.0002016256,0.01545013,0.02402825,0.001037565,0.0001384071,0.0001317332,0.00000621569,0.0004796784],"genre_scores_gemma":[0.9512295,0.0004337657,0.03420049,0.01358868,0.0004787058,0.000004405379,0.00002879292,0.000009494591,0.0000262003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07086293,"threshold_uncertainty_score":0.9734633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4388500127733003,"score_gpt":0.556197554520424,"score_spread":0.1173475417471236,"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."}}