{"id":"W1991724805","doi":"10.1186/1472-6947-11-53","title":"De-identifying a public use microdata file from the Canadian national discharge abstract database","year":2011,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Health Information; Agricultural Research Institute of Ontario","funders":"Canadian Institutes of Health Research; CHEO Research Institute; Ontario Institute for Cancer Research; Google","keywords":"Microdata (statistics); Health informatics; Computer science; Data quality; Data mining; Data set; Identification (biology); Data file; Information retrieval; Data collection; Database; Set (abstract data type); Public health; Data science; Medicine; Statistics; Population; Census; Environmental health; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004763775,0.0001415297,0.0001984365,0.000178992,0.001987831,0.0001988661,0.000461869,0.0003084337,0.02083846],"category_scores_gemma":[0.01182423,0.000091501,0.00004132904,0.0001906891,0.0001063265,0.001018939,0.0003149964,0.00102532,0.0005867819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001985432,"about_ca_system_score_gemma":0.003820082,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02382555,"about_ca_topic_score_gemma":0.1544748,"domain_scores_codex":[0.9966515,0.0001262415,0.001258456,0.0001271002,0.001219963,0.000616691],"domain_scores_gemma":[0.9906618,0.007390225,0.0004047193,0.0003520719,0.0002392189,0.0009519662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009979605,0.00005113032,0.05002547,0.0006700985,0.00003405767,0.00001164146,0.01971626,0.000002785889,7.835833e-7,0.01851731,0.7327864,0.1780843],"study_design_scores_gemma":[0.001949749,0.00003349967,0.204707,0.006470208,0.00003222176,0.0000341888,0.01154683,0.4232793,0.000001011775,0.01242666,0.339015,0.0005043136],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3085397,0.0003494939,0.6339065,0.001291724,0.002371892,0.001591123,0.005816865,0.0002127003,0.04591997],"genre_scores_gemma":[0.6852585,0.0002841351,0.2715465,0.04002159,0.0006675783,0.0001214533,0.001960533,0.00002770931,0.000111969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4232765,"threshold_uncertainty_score":0.9993114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5616257091682858,"score_gpt":0.4819889484445266,"score_spread":0.07963676072375925,"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."}}