{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003445981,0.001218398,0.001816942,0.004536222,0.001326125,0.004335825,0.002789547,0.001806917,0.00289933],"category_scores_gemma":[0.009676991,0.0007012007,0.002359294,0.003776439,0.0009388976,0.002657813,0.003797992,0.001860284,0.001501311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001515895,"about_ca_system_score_gemma":0.006445234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0114418,"about_ca_topic_score_gemma":0.01982467,"domain_scores_codex":[0.9955776,0.0008693967,0.0004778017,0.0008355016,0.001847233,0.0003924948],"domain_scores_gemma":[0.9958854,0.001597085,0.0004549334,0.0007784443,0.00106163,0.0002225701],"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":[0.0008016973,0.0006300449,0.006055882,0.0006386455,0.000315481,0.0006531085,0.0005938997,0.1301951,0.0323736,0.08453079,0.0199586,0.7232532],"study_design_scores_gemma":[0.00004941667,0.00008211128,0.0008356561,0.00004040644,0.00007771391,0.0002680407,0.0001187214,0.9448628,0.009345589,0.0390006,0.00527409,0.00004491011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003706391,0.0001966112,0.9919309,0.0001599036,0.00003473394,0.0001386713,0.0004868893,0.002943285,0.0004025557],"genre_scores_gemma":[0.08324284,0.0001640061,0.9137446,0.0001082028,0.0000726731,0.000165703,0.00142301,0.0001690897,0.0009098996],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0114418,"threshold_uncertainty_score":0.02275038,"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."}}