{"id":"W4413052408","doi":"10.3233/shti251231","title":"An Iterative Composite Method for the De-Identification of Medical Notes","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Identification (biology); Computer science; Identifier; Matching (statistics); Security token; Medical record; Iterative method; Artificial intelligence; Residual; Machine learning; Data mining; Algorithm; Medicine; Statistics; Computer security; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.002411264,0.00006232908,0.0001949563,0.000361003,0.0002095567,0.0000178002,0.0004793422,0.0001163315,3.759404e-7],"category_scores_gemma":[0.0006923529,0.00004441313,0.00001433065,0.0005605583,0.0002930437,0.000191359,0.0001923309,0.0001731798,2.154314e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003806293,"about_ca_system_score_gemma":0.00009478649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001035484,"about_ca_topic_score_gemma":0.00002271836,"domain_scores_codex":[0.9989902,0.00006584369,0.0006253899,0.00007661858,0.00009877375,0.0001431952],"domain_scores_gemma":[0.9984831,0.000902787,0.0002077641,0.0002379127,0.0001510713,0.00001734108],"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":[0.000003678604,0.00002578782,0.0007448792,0.0004761104,0.00002845105,1.36753e-7,0.007601978,0.000008210124,0.00001690947,0.3896803,0.0001431685,0.6012704],"study_design_scores_gemma":[0.0004612046,0.0003128564,0.001418685,0.0004407342,0.000009105732,0.00001636863,0.007801667,0.6911777,0.01538212,0.2810718,0.00180447,0.0001032653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002293483,0.001794365,0.9762929,0.01900903,0.00009175839,0.0003820689,0.000002924095,0.0001029419,0.00003050371],"genre_scores_gemma":[0.4433596,0.003492889,0.5506201,0.002264754,0.000006081296,0.0002473516,0.000001860239,0.000002014005,0.000005385976],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6911694,"threshold_uncertainty_score":0.1811115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0406133108800299,"score_gpt":0.4391572423483992,"score_spread":0.3985439314683693,"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."}}