{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.03589801,0.0002118344,0.0007976916,0.0002325598,0.0009155175,0.001264061,0.0006161765,0.00006275247,0.00002720971],"category_scores_gemma":[0.004025183,0.0001844384,0.0001034045,0.0009025058,0.00004103681,0.0009505491,0.0002547151,0.0002017979,0.00001172396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001288831,"about_ca_system_score_gemma":0.0006268857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001779225,"about_ca_topic_score_gemma":0.0003295292,"domain_scores_codex":[0.9933244,0.002642713,0.001474345,0.001011995,0.0006849662,0.0008615874],"domain_scores_gemma":[0.9945869,0.002618274,0.0007793552,0.0005312453,0.0003616878,0.001122547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003191302,0.0001565292,0.009226123,0.0002200274,0.00002439523,1.861682e-7,0.00393984,0.000003537349,7.274317e-7,0.00136536,0.02170078,0.9633306],"study_design_scores_gemma":[0.001303616,0.0008859141,0.01240277,0.000005118445,5.976005e-7,0.000001231966,0.01138217,0.0238232,3.783524e-7,0.002187913,0.9478015,0.0002055896],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009588611,0.0002162932,0.8445745,0.1415746,0.0006563382,0.003023881,0.0001131756,0.0001360883,0.0001165617],"genre_scores_gemma":[0.470181,0.0003944709,0.4758563,0.04827467,0.001416417,0.002114537,0.0009208716,0.00007605656,0.0007656086],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.963125,"threshold_uncertainty_score":0.9997727,"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."}}