{"id":"W2999189714","doi":"10.2196/15917","title":"Comparing Methods for Record Linkage for Public Health Action: Matching Algorithm Validation Study","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Record linkage; Precision and recall; Context (archaeology); Computer science; Public health; Matching (statistics); Algorithm; Linkage (software); Data mining; Psychological intervention; Medicine; Population; Machine learning; Statistics; Mathematics; Environmental health; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3686821,0.001906204,0.002368513,0.003751619,0.002030472,0.003258566,0.004624079,0.004129475,0.003537831],"category_scores_gemma":[0.6049316,0.00144357,0.007241153,0.00429608,0.002129555,0.006671721,0.004828468,0.004208232,0.0005316209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005749434,"about_ca_system_score_gemma":0.008179414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008835145,"about_ca_topic_score_gemma":0.004453322,"domain_scores_codex":[0.6257295,0.3396651,0.01104357,0.009794334,0.01231293,0.001454489],"domain_scores_gemma":[0.2152369,0.7230928,0.01608187,0.02620036,0.01862878,0.000759367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01858812,0.004161111,0.2227376,0.005913587,0.02875571,0.0002096636,0.003492174,0.35543,0.0007162268,0.0352705,0.007857197,0.3168682],"study_design_scores_gemma":[0.004948946,0.006191796,0.02631497,0.001393706,0.004609703,0.0003362668,0.0007874083,0.9208828,0.0018932,0.02628983,0.006068611,0.0002827808],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3740459,0.007338817,0.6008219,0.002239054,0.000555942,0.008054861,0.001926705,0.0009649806,0.004051849],"genre_scores_gemma":[0.6937681,0.001052025,0.2952469,0.0006861743,0.000125519,0.006553769,0.001702135,0.0002437516,0.0006215351],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3686821,"threshold_uncertainty_score":0.7785274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5653348348544291,"score_gpt":0.5458407834458321,"score_spread":0.01949405140859706,"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."}}