{"id":"W4389615820","doi":"10.23889/ijpds.v8i1.2153","title":"De-identification of Free Text Data containing Personal Health Information: A Scoping Review of Reviews","year":2023,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; George & Fay Yee Centre for Healthcare Innovation; Manitoba Health","funders":"Canadian Institutes of Health Research","keywords":"Health Insurance Portability and Accountability Act; Identification (biology); Computer science; Protected health information; Information retrieval; MEDLINE; Personally identifiable information; Digital library; Data science; World Wide Web; Medicine; Confidentiality; Public health; Nursing; Health education","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07437966,0.0002260038,0.001452608,0.001358967,0.0003325671,0.000942666,0.01807817,0.00006471051,0.0001177237],"category_scores_gemma":[0.06575675,0.0001738314,0.0002589187,0.001797931,0.0002218254,0.009249598,0.00429955,0.0002499947,0.00006816018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002908427,"about_ca_system_score_gemma":0.00256063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001499297,"about_ca_topic_score_gemma":0.00007457093,"domain_scores_codex":[0.9875827,0.0005568905,0.006617116,0.0007229413,0.004216212,0.0003041784],"domain_scores_gemma":[0.9813532,0.001399557,0.01186457,0.003379878,0.001826005,0.0001768051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005910315,0.00001944298,0.000008429448,0.02713372,0.00004269615,4.79978e-7,0.00009950463,0.000004131516,1.175437e-7,0.002443268,0.03728007,0.9329622],"study_design_scores_gemma":[0.0001305442,0.00002847095,0.0000380855,0.2207394,0.00009487045,0.00003741265,0.00009098175,0.00204625,1.13359e-7,0.000857024,0.7758035,0.0001333251],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.649742e-7,0.9250688,0.05741154,0.001183291,0.002280572,0.001791003,0.01219702,0.00001425928,0.00005314205],"genre_scores_gemma":[0.000005274331,0.9843192,0.004617844,0.0004737379,0.0002315402,0.0000310523,0.01021494,0.00001095169,0.00009548473],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9328289,"threshold_uncertainty_score":0.9872345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7026193400916434,"score_gpt":0.6308973187983484,"score_spread":0.07172202129329497,"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."}}