{"id":"W2148059418","doi":"10.1186/1472-6947-10-35","title":"De-identification of primary care electronic medical records free-text data in Ontario, Canada","year":2010,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Institute for Clinical Evaluative Sciences","funders":"York University","keywords":"Medical record; Text messaging; Protected health information; Identification (biology); Health informatics; Computer science; Context (archaeology); Set (abstract data type); Information retrieval; Medicine; World Wide Web; Public health; Nursing; Health policy","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":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007889712,0.0001666822,0.0005091798,0.0001784666,0.0002564768,0.00001958827,0.001203777,0.0005967155,0.001301608],"category_scores_gemma":[0.005589624,0.0001402654,0.00002802816,0.000245848,0.00007502569,0.0002343842,0.0007820356,0.002719814,0.00001189338],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001388308,"about_ca_system_score_gemma":0.06118978,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6839461,"about_ca_topic_score_gemma":0.9987717,"domain_scores_codex":[0.9940088,0.0002554578,0.00268187,0.0002368097,0.00196353,0.000853497],"domain_scores_gemma":[0.9928945,0.00450582,0.0007217478,0.001192351,0.0001897131,0.0004958792],"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":[0.0001892052,0.00006110964,0.278836,0.003828701,0.00001990357,0.00001536797,0.005227643,0.00001008849,0.00001166189,0.003158044,0.018163,0.6904793],"study_design_scores_gemma":[0.00772231,0.0002534877,0.2292015,0.01065488,0.00005760063,0.0001948448,0.01409504,0.5133803,0.000009378356,0.007348232,0.2161623,0.0009201196],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9390927,0.000437902,0.05324196,0.0001043923,0.001488219,0.0006517082,0.00003160228,0.00002495183,0.004926554],"genre_scores_gemma":[0.9786904,0.0002515409,0.01849865,0.001949529,0.0002362878,0.00005983298,0.000170539,0.0000256251,0.000117634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6895592,"threshold_uncertainty_score":0.9996113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05042003103964154,"score_gpt":0.39875889996687,"score_spread":0.3483388689272285,"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."}}