{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0143123,0.0006439448,0.001146826,0.003709545,0.001012245,0.002209777,0.002135958,0.001650896,0.001084686],"category_scores_gemma":[0.03726062,0.0005595259,0.001414521,0.003391258,0.0004855109,0.001557119,0.002448036,0.0007992038,0.0005145489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00219876,"about_ca_system_score_gemma":0.003982021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01209246,"about_ca_topic_score_gemma":0.006404801,"domain_scores_codex":[0.9918514,0.00337491,0.001170338,0.002136139,0.001129772,0.0003375177],"domain_scores_gemma":[0.9861442,0.009192499,0.001189163,0.001345544,0.001936159,0.0001923544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009367926,0.000818583,0.1820307,0.0003426861,0.0007985944,0.0004402625,0.0004543389,0.2142797,0.005554573,0.006359094,0.004974216,0.5830105],"study_design_scores_gemma":[0.000246527,0.0002188017,0.02519019,0.00003862691,0.0001393376,0.0006379753,0.0001639481,0.9585945,0.004976306,0.006664312,0.003089497,0.00003990851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.254043,0.0007012057,0.7382501,0.0007361214,0.00006523394,0.0007043654,0.0008441265,0.003466654,0.001189181],"genre_scores_gemma":[0.3924445,0.000135544,0.6040943,0.000180034,0.00003509216,0.0004581952,0.002016534,0.00008393513,0.0005519016],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0143123,"threshold_uncertainty_score":0.07569158,"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."}}