{"id":"W4226372432","doi":"10.2196/36711","title":"Linking Biomedical Data Warehouse Records With the National Mortality Database in France: Large-scale Matching Algorithm","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Conseil Régional des Pays de la Loire; Agence Nationale de la Recherche","keywords":"Algorithm; Database; Matching (statistics); Computer science; Data mining; Identifier; Scale (ratio); Medicine; Statistics; Mathematics; Cartography; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02538717,0.000165328,0.00030511,0.0002628878,0.0005432549,0.0002676303,0.004369222,0.00007761544,0.00196483],"category_scores_gemma":[0.001032296,0.0000986364,0.0000436065,0.001468897,0.0002940421,0.001419559,0.005353059,0.00109574,0.0001147179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008559029,"about_ca_system_score_gemma":0.0004332694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001066392,"about_ca_topic_score_gemma":0.0003782206,"domain_scores_codex":[0.9876535,0.0004307507,0.001358301,0.0003490544,0.009769137,0.0004392904],"domain_scores_gemma":[0.9966527,0.001176773,0.0004054044,0.00141159,0.0001061247,0.0002474247],"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":[0.00005379168,0.001635594,0.005570343,0.0001935956,0.0001196227,0.0001614946,0.03640609,0.0005610575,9.374655e-7,0.003979421,0.6942838,0.2570343],"study_design_scores_gemma":[0.0008177545,0.000049124,0.00211674,0.00004727357,0.000008542575,0.00002241245,0.02467888,0.245315,4.233389e-7,0.001873649,0.7249083,0.0001619037],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1389079,0.00008071556,0.8230654,0.02116496,0.001472993,0.00142647,0.009549318,0.000214952,0.004117312],"genre_scores_gemma":[0.4961283,0.0003504378,0.2483474,0.206972,0.003211664,0.002011086,0.03816611,0.0001791386,0.004633857],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5747179,"threshold_uncertainty_score":0.9989475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1245525492908599,"score_gpt":0.4246629664904805,"score_spread":0.3001104171996207,"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."}}