{"id":"W4225160911","doi":"10.1016/j.compeleceng.2022.107985","title":"An efficient framework for semantically-correlated term detection and sanitization in clinical documents","year":2022,"lang":"en","type":"article","venue":"Computers & Electrical Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brandon University","funders":"","keywords":"Term (time); Computer science; Information retrieval; Data mining; Physics","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":[0.002456744,0.0001062459,0.0002253441,0.0003271386,0.0001400729,0.0001793478,0.0003741964,0.0000602633,0.00001451627],"category_scores_gemma":[0.001129727,0.0001049639,0.00005707102,0.0009333296,0.0000170073,0.0001334027,0.000216558,0.0003303809,0.000004130835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009263118,"about_ca_system_score_gemma":0.00001512986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005342571,"about_ca_topic_score_gemma":0.000001096819,"domain_scores_codex":[0.9979817,0.0001830662,0.0006225937,0.0004668723,0.0004784266,0.0002672887],"domain_scores_gemma":[0.9979597,0.001541616,0.00008726907,0.0002651185,0.00003728933,0.0001090424],"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":[0.0001222683,0.0004148229,0.001061373,0.00001602748,0.0000275383,0.0000153834,0.0002833065,0.5074108,0.0002585158,0.02781989,0.0002521071,0.462318],"study_design_scores_gemma":[0.0004372486,0.0003256581,0.01500252,0.000009446644,0.000008785568,0.000003974806,0.00002377892,0.9778281,0.00002867543,0.004250953,0.001950767,0.0001301256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2324127,0.00003348155,0.7665279,0.00009639789,0.000587642,0.0002705091,0.000003089768,0.00006125379,0.000007055775],"genre_scores_gemma":[0.9880182,0.000005319081,0.01159763,0.0002420075,0.00006437431,0.00004018975,0.00001293065,0.00001108461,0.00000827474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7556055,"threshold_uncertainty_score":0.4280305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04488731065467413,"score_gpt":0.3768482874448765,"score_spread":0.3319609767902024,"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."}}