{"id":"W2098161667","doi":"10.2196/jmir.8.4.e28","title":"Evaluating Common De-Identification Heuristics for Personal Health Information","year":2006,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Agricultural Research Institute of Ontario","funders":"Ontario Centres of Excellence","keywords":"Observational study; Heuristics; Health Insurance Portability and Accountability Act; Identification (biology); Protected health information; Agency (philosophy); Personally identifiable information; Confidentiality; Internet privacy; Accountability; Data science; Computer science; Medicine; Nursing; Computer security; HRHIS; Public health; Health policy; Political science; Sociology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09346315,0.00008379589,0.0003571715,0.0004450714,0.000123122,0.0001418447,0.0005136128,0.0003992326,0.0004053844],"category_scores_gemma":[0.08951686,0.00006528089,0.0001751547,0.00028472,0.0004088003,0.0001818218,0.0001556539,0.00452002,0.00004260059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007458862,"about_ca_system_score_gemma":0.00450686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005746736,"about_ca_topic_score_gemma":0.0001645065,"domain_scores_codex":[0.988414,0.0007183858,0.001733019,0.0001439998,0.008431463,0.0005591293],"domain_scores_gemma":[0.9792024,0.01434129,0.0005551614,0.0002115568,0.004945696,0.0007438285],"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":[0.00418117,0.001901647,0.0214396,0.004762202,0.0002655339,0.0001832093,0.004907642,0.00002770213,0.001241853,0.03877036,0.4449498,0.4773692],"study_design_scores_gemma":[0.01422895,0.01933342,0.07219703,0.00894024,0.000113115,0.002108351,0.003873885,0.6447361,0.003791191,0.1452694,0.08503243,0.0003759349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7592079,0.0009416767,0.06981848,0.167029,0.0005903374,0.0009543482,0.00001620222,0.00002179773,0.001420245],"genre_scores_gemma":[0.9917309,0.0004621262,0.003455708,0.0009893323,0.001290825,0.00001806851,0.00003445516,0.00001505297,0.002003547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6447084,"threshold_uncertainty_score":0.9977766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6632204600192323,"score_gpt":0.7130576617179335,"score_spread":0.04983720169870121,"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."}}