{"id":"W4283574083","doi":"10.1016/j.jclinepi.2022.06.006","title":"Record linkage and big data—enhancing information and improving design","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba; Manitoba Health","funders":"Canadian Institutes of Health Research","keywords":"Linkage (software); Record linkage; Computer science; Data science; Observational study; Population; Value (mathematics); Data mining; Medicine; Statistics; Mathematics; Environmental health; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2113508,0.001576833,0.003684016,0.006335589,0.002077861,0.01707494,0.006269911,0.004470346,0.004695209],"category_scores_gemma":[0.5631618,0.00260926,0.00288673,0.009719012,0.003454963,0.03182435,0.01020895,0.006746619,0.001251888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003316474,"about_ca_system_score_gemma":0.0131299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002391178,"about_ca_topic_score_gemma":0.002612312,"domain_scores_codex":[0.7546747,0.1967758,0.01559479,0.008849694,0.02268381,0.001421166],"domain_scores_gemma":[0.2195042,0.646808,0.02699243,0.07333267,0.02969424,0.003668371],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001988813,0.001121263,0.06285077,0.006435574,0.002903572,0.0001521923,0.003579042,0.01286621,0.002221162,0.08957896,0.03035701,0.7859453],"study_design_scores_gemma":[0.002153742,0.001852468,0.02072433,0.004806265,0.003906571,0.0006636714,0.003193296,0.136488,0.01507386,0.7104971,0.09996305,0.0006776588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03693431,0.016206,0.8348786,0.09551904,0.002161248,0.001878016,0.002135908,0.003613437,0.006673418],"genre_scores_gemma":[0.2050785,0.005469739,0.7748575,0.008197725,0.001912385,0.001507311,0.001545777,0.0004242794,0.001006888],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7886492,"threshold_uncertainty_score":0.9725448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7736697826487204,"score_gpt":0.5786307282052613,"score_spread":0.1950390544434591,"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."}}