{"id":"W4406694526","doi":"10.1093/jamiaopen/ooae152","title":"pyDeid: an improved, fast, flexible, and generalizable rule-based approach for deidentification of free-text medical records","year":2024,"lang":"en","type":"article","venue":"JAMIA Open","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Hospital for Sick Children; St. Michael's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canadian Frailty Network; Canadian Cancer Society","keywords":"Computer science; Python (programming language); Software; Precision and recall; Identification (biology); Benchmark (surveying); Data mining; Artificial intelligence; Extant taxon; Flexibility (engineering); Machine learning; Recall; Information retrieval; Natural language processing; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007651795,0.001682661,0.001460371,0.005303482,0.0009901244,0.003953929,0.004954693,0.001291187,0.005721098],"category_scores_gemma":[0.03183748,0.001095087,0.0020854,0.003189991,0.001040951,0.004078426,0.005909091,0.002957626,0.005748603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001273091,"about_ca_system_score_gemma":0.005560177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006617357,"about_ca_topic_score_gemma":0.007341954,"domain_scores_codex":[0.9911649,0.001205914,0.001688199,0.002282124,0.003367348,0.0002915301],"domain_scores_gemma":[0.9864669,0.006346565,0.001491744,0.00287691,0.002330129,0.0004876865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001154658,0.0005759577,0.02532645,0.002732219,0.0006706291,0.001550558,0.001077065,0.02077716,0.01681793,0.01288459,0.199582,0.7168509],"study_design_scores_gemma":[0.0006567708,0.0003764525,0.01710661,0.0008988712,0.0002611674,0.004362083,0.0006577267,0.4882409,0.09108159,0.0499218,0.3458259,0.0006101639],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01338821,0.001034361,0.7202505,0.001175792,0.0004170476,0.001170253,0.02952912,0.229138,0.0038968],"genre_scores_gemma":[0.05705756,0.0007551227,0.8717951,0.001505664,0.0001180358,0.000862275,0.05706061,0.005064494,0.005781098],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007651795,"threshold_uncertainty_score":0.04046702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03624260455257254,"score_gpt":0.3462986527902708,"score_spread":0.3100560482376983,"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."}}