{"id":"W3168932797","doi":"10.1186/s12911-021-01550-6","title":"Record linkage under suboptimal conditions for data-intensive evaluation of primary care in Rio de Janeiro, Brazil","year":2021,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Medical Research Council; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Record linkage; Identifier; Linkage (software); Probabilistic logic; Quality (philosophy); Gold standard (test); Health informatics; Computer science; Database; Health care; Data quality; Data mining; Medicine; Public health; Artificial intelligence; Population; Environmental health; Nursing; Business; Service (business)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01204477,0.0001119076,0.0003722236,0.0002604074,0.0001188358,0.0002189359,0.0006503839,0.0001371624,0.0003830515],"category_scores_gemma":[0.0193944,0.00008898576,0.00006838472,0.0004123785,0.0001174539,0.0006446728,0.0009651841,0.000157858,0.00001790767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009291431,"about_ca_system_score_gemma":0.001054281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001349535,"about_ca_topic_score_gemma":0.001161952,"domain_scores_codex":[0.9951724,0.0002350731,0.001472003,0.0002665982,0.002634622,0.000219272],"domain_scores_gemma":[0.9896215,0.007612692,0.0004042603,0.0008271479,0.001397848,0.0001365335],"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":[0.0001024671,0.00005382181,0.0009991925,0.0002183656,0.00001667035,0.000006018803,0.001543506,0.002465099,0.000003596892,0.004382215,0.01438913,0.9758199],"study_design_scores_gemma":[0.001820216,0.00005258458,0.007180143,0.0005871549,0.00005682893,0.00001666731,0.02783993,0.8885913,0.000008713746,0.06685252,0.00685756,0.0001363804],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2179191,0.0003097574,0.7778837,0.0001028474,0.0002557236,0.0003221228,0.0002527396,0.000008469042,0.002945529],"genre_scores_gemma":[0.4442871,0.0002601737,0.5476393,0.006214738,0.00008724057,0.00004171622,0.001400015,0.00001294208,0.00005679648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9756835,"threshold_uncertainty_score":0.9888657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.321064875369702,"score_gpt":0.5008400079838637,"score_spread":0.1797751326141618,"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."}}