{"id":"W3095788424","doi":"10.1038/s41598-020-75544-1","title":"De-identification of electronic health record using neural network","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Identification (biology); Process (computing); Health records; Compromise; Artificial neural network; Data mining; Mechanism (biology); Data anonymization; Artificial intelligence; Machine learning; Information sensitivity; Data science; Quality (philosophy); Information retrieval; Information privacy; Health care; Computer security","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":[0.003098592,0.0001127598,0.0002206517,0.00008514652,0.0003755515,0.0002979373,0.0005131814,0.00004407748,0.00001808476],"category_scores_gemma":[0.0002924213,0.0001176617,0.00007974488,0.00135663,0.00007663228,0.0002980279,0.0001874734,0.0002669853,0.000006262269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001560448,"about_ca_system_score_gemma":0.001019103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002357606,"about_ca_topic_score_gemma":0.00002235012,"domain_scores_codex":[0.9969084,0.0002732001,0.0008866398,0.0008140592,0.0004936726,0.000624027],"domain_scores_gemma":[0.9975773,0.00004035515,0.001007682,0.0009651404,0.000173609,0.0002359172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002335991,0.0001156245,0.2212716,0.0007420919,0.00004380551,0.0002453108,0.008814273,0.4986147,0.01723999,0.01557406,0.028802,0.2085132],"study_design_scores_gemma":[0.00004509175,0.00008768538,0.003870326,0.00002917067,0.000003599915,0.0001536468,0.000018097,0.9738204,0.0006741797,0.0085237,0.0126396,0.0001345094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6199912,0.0008016238,0.362445,0.008956759,0.006864183,0.0005062467,7.01558e-7,0.0003123118,0.000121963],"genre_scores_gemma":[0.9845021,0.000003402144,0.01470735,0.0004852388,0.0001543585,0.00000481413,0.000007636867,0.00001175669,0.0001233869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4752057,"threshold_uncertainty_score":0.4798103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03266138406027824,"score_gpt":0.3162253936720649,"score_spread":0.2835640096117866,"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."}}