{"id":"W2413622533","doi":"10.1093/ije/dyw075","title":"Maelstrom Research guidelines for rigorous retrospective data harmonization","year":2016,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":272,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Ontario Institute for Cancer Research; McMaster University; McGill University Health Centre","funders":"Economic and Social Research Council; Medical Research Council; European Commission; Government of Ontario; Wellcome Trust; Partenariat Canadien Contre Le Cancer; University of Bristol; Canadian Institutes of Health Research; Genome Canada","keywords":"Harmonization; Standardization; Computer science; Interdependence; Data science; Data quality; Management science; Inefficiency; Process management; Service (business); Business; Political science; Engineering; Law","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03033094,0.00008121627,0.0003626726,0.00031389,0.0002750891,0.000004185789,0.0009659494,0.0002206451,0.000596109],"category_scores_gemma":[0.1792491,0.00004712503,0.00005947803,0.00008897006,0.0001303517,0.0003906416,0.0002222756,0.0005747786,0.0001500678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004885821,"about_ca_system_score_gemma":0.0006249119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006635353,"about_ca_topic_score_gemma":0.00002889563,"domain_scores_codex":[0.99532,0.001420464,0.002143316,0.0001914918,0.0004908575,0.0004339329],"domain_scores_gemma":[0.9756521,0.01252297,0.001421884,0.0003261691,0.00988039,0.0001964914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004942121,0.00002684677,0.0770784,0.00003666873,0.00009269299,0.000004238141,0.0002424816,0.000008147736,0.0001670299,0.04130189,0.812304,0.06824335],"study_design_scores_gemma":[0.002368683,0.0003840306,0.04159765,0.000830777,0.00001592441,0.00004069824,0.0003140806,0.002649163,0.00001941739,0.0977874,0.8538994,0.00009276628],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01370608,0.0004455184,0.6469598,0.3282716,0.007878886,0.0004711904,0.0003243943,0.00002359356,0.001918891],"genre_scores_gemma":[0.7678973,0.006158649,0.1502759,0.04076356,0.02788717,0.0001113597,0.0004163007,0.00006128704,0.006428486],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7541912,"threshold_uncertainty_score":0.9984784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9102577888579144,"score_gpt":0.7132176123109125,"score_spread":0.1970401765470019,"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."}}