{"id":"W3012211566","doi":"10.2196/17622","title":"Re-examination of Rule-Based Methods in Deidentification of Electronic Health Records: Algorithm Development and Validation","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Rule-based system; Task (project management); Machine learning; Artificial intelligence; Data mining; Health informatics; Set (abstract data type); Ensemble learning; Health records; Reliability (semiconductor); Health care","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002930348,0.00008165849,0.000222804,0.0001650206,0.00003472554,0.00001811512,0.0003214083,0.00008960306,0.00001204127],"category_scores_gemma":[0.000525824,0.00007899925,0.00001766977,0.0005559797,0.0000366845,0.0002638221,0.00008671104,0.0002823573,0.000002188698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001139225,"about_ca_system_score_gemma":0.0007847734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003191724,"about_ca_topic_score_gemma":0.0000134008,"domain_scores_codex":[0.9976797,0.0003677939,0.001069372,0.0001119696,0.0005853496,0.0001858708],"domain_scores_gemma":[0.9987083,0.0002622615,0.0005836048,0.0001800884,0.0001163656,0.0001493443],"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":[0.000002760011,0.00003031829,0.0009292338,0.0007700744,0.000003453496,1.92597e-7,0.01664953,0.00006642836,0.000006446525,0.001419534,0.00002763125,0.9800944],"study_design_scores_gemma":[0.0003860153,0.000168759,0.01590057,0.0001640728,0.000001276971,0.000001125852,0.0005397341,0.9790836,0.002627738,0.0001726733,0.0008763974,0.00007806256],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05745454,0.00005063627,0.9389414,0.003085957,0.0000489851,0.0003010545,8.683141e-7,0.00003902295,0.00007754273],"genre_scores_gemma":[0.2522813,0.00002505108,0.7469278,0.0006868714,0.0000117654,0.00002751546,0.0000328284,0.000004318166,0.000002527177],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9800164,"threshold_uncertainty_score":0.3221496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03716599547608451,"score_gpt":0.3833501845760687,"score_spread":0.3461841890999842,"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."}}